Compare commits

...

69 Commits

Author SHA1 Message Date
João Moura
e2113fe417 preparing new verions 2024-07-19 13:22:28 -04:00
Eduardo Chiarotti
f9288295e6 fix: agent missing fix (#966) 2024-07-19 13:15:33 -03:00
João Moura
fcc57f2fc0 rmeoving extra logging 2024-07-19 01:16:15 -04:00
Dev Khant
5cb6ee9eeb Docs: Update info about tools (#896) 2024-07-19 01:38:42 -03:00
ariel
b38f0825e7 Fix broken link to the installation guide (#912)
Updated the installation guide link to use the absolute URL instead of a relative path, ensuring it correctly points to 'https://docs.crewai.com/how-to/Installing-CrewAI/'.
2024-07-19 01:37:54 -03:00
Salman Faroz
f51e94dede Update Crews.md (#889)
To solve :
I encountered an error while trying to use the tool. This was the error: DuckDuckGoSearchRun._run() got an unexpected keyword argument 'q'.
 Tool duckduckgo_search accepts these inputs: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.

refer : https://github.com/joaomdmoura/crewAI/issues/316
2024-07-19 01:37:24 -03:00
robbyriverside
47bf93d291 Update Memory.md (#728)
The memory documentation left me with a lot of questions.  After I went through the code to find an answer.  I added this paragraph to explain what I found.  Hope this is helpful.
2024-07-19 01:36:54 -03:00
Braelyn Boynton
41fd1c6124 upgrade agentops to 0.3 (#957)
* upgrade agentops to 0.3

* lockfile
2024-07-18 13:30:04 -03:00
Lorenze Jay
be1b9a3994 Reset memory (#958)
* reseting memory on cli

* using storage.reset

* deleting memories on command

* added tests

* handle when no flags are used

* added docs
2024-07-18 13:29:42 -03:00
Eduardo Chiarotti
61a196394b feat: Add planning feature to crew (#919)
* feat: add planning feature to crew

* feat: add test to planning handler and change to execute_async method

* docs: add planning parameter to the Core documentation

* docs: add planning docs

* fix: fix type checking issue

* fix: test and logic
2024-07-18 13:15:08 -03:00
Lorenze Jay
5b442e4350 Merge pull request #951 from crewAIInc/test-hierarchical-tools-proper-setup
Test hierarchical tools proper setup
2024-07-17 08:53:23 -07:00
Lorenze Jay
c9920b9823 better spacing 2024-07-17 08:40:52 -07:00
Lorenze Jay
2faa2dbddb code cleanup 2024-07-17 08:39:57 -07:00
Lorenze Jay
76607062f0 using gpt4o 2024-07-17 08:27:43 -07:00
Lorenze Jay
a8cac9b7e9 Merge branch 'main' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-17 08:21:13 -07:00
Brandon Hancock (bhancock_ai)
dfacc8832f Merge pull request #954 from crewAIInc/hotfix/improve-async-logging
Fix logging for async and sync tasks
2024-07-17 11:20:13 -04:00
Lorenze Jay
93f643f851 fixed test 2024-07-17 08:20:05 -07:00
Brandon Hancock
cbf5d548be Merge branch 'main' into hotfix/improve-async-logging 2024-07-17 11:17:23 -04:00
Lorenze Jay
6946b89e17 Merge branch 'main' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-17 08:16:44 -07:00
Brandon Hancock (bhancock_ai)
dc4911b1ca Merge pull request #950 from crewAIInc/conditional-task-f
conditional task feat
2024-07-17 11:08:06 -04:00
Brandon Hancock
6ad218f9a0 Fix issues found by linter 2024-07-17 11:05:31 -04:00
Brandon Hancock
36efa172ee Add more tests. Clean up docs. Improve conditional task 2024-07-17 11:03:11 -04:00
Brandon Hancock
a7a2dfd296 Fix logging 2024-07-17 10:10:34 -04:00
João Moura
7baaeacac3 Adding better support for open source tool calling models (#952)
* Adding better support for open source tool calling models

* making sure the right tool is called

* fixing tests

* better support opensource models
2024-07-17 05:54:13 -03:00
Lorenze Jay
021f2eb8a1 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:35:27 -07:00
Lorenze Jay
cb720143c7 Merge branch 'main' of github.com:joaomdmoura/crewAI into conditional-task-f 2024-07-16 20:34:35 -07:00
Lorenze Jay
731de2ff31 Merge branch 'test-hierarchical-tools-proper-setup' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:31:42 -07:00
Lorenze Jay
24e28da203 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:28:50 -07:00
Lorenze Jay
bde0a3e99c code cleanup 2024-07-16 20:11:52 -07:00
Lorenze Jay
0415b9982b code cleanup 2024-07-16 20:07:05 -07:00
Brandon Hancock (bhancock_ai)
99ada42d97 Merge pull request #941 from crewAIInc/bugfix/minor-max-retry-recursion-fix
Properly capture result from max retry recursive call
2024-07-16 22:05:58 -04:00
Lorenze Jay
ee32d36312 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 16:05:09 -07:00
Lorenze Jay
ef928ee3cb added docs and tests 2024-07-16 16:04:41 -07:00
Lorenze Jay
c66559345f Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 15:20:46 -07:00
Lorenze Jay
3ad95d50d4 ensures _update_manager_tools has a manager otherwise throw error 2024-07-16 15:15:50 -07:00
Lorenze Jay
bc7f601f84 updated fixes for conditional tasks 2024-07-16 15:10:13 -07:00
Lorenze Jay
e8cbdb7881 fixed hierarchial manager tools when assigned an agent 2024-07-16 14:00:25 -07:00
Lorenze Jay
b0c2b15a3e better code spacing 2024-07-16 13:07:31 -07:00
Lorenze Jay
c0f04bbb37 removing unused code 2024-07-16 13:06:50 -07:00
Lorenze Jay
c320fc655e conditional task feat 2024-07-16 12:04:34 -07:00
Brandon Hancock (bhancock_ai)
ac2815c781 Add docs for crewoutput and taskoutput (#943)
* Add docs for crewoutput and taskoutput

* Add reference to change log
2024-07-15 21:39:15 -03:00
Gui Vieira
dd8a199e99 Introduce structure keys (#902)
* Introduce structure keys

* Add agent key to tasks

* Rebasing is hard

* Rename task output telemetry

* Feedback
2024-07-15 19:37:07 -03:00
Gui Vieira
161c4a6856 Fix crew creation telemetry (#939)
* Fix crew creation telemetry

* Remove task index
2024-07-15 17:43:57 -03:00
Lorenze Jay
67b04b30bf Replay feat using db (#930)
* Cleaned up task execution to now have separate paths for async and sync execution. Updating all kickoff functions to return CrewOutput. WIP. Waiting for Joao feedback on async task execution with task_output

* Consistently storing async and sync output for context

* outline tests I need to create going forward

* Major rehaul of TaskOutput and CrewOutput. Updated all tests to work with new change. Need to add in a few final tricky async tests and add a few more to verify output types on TaskOutput and CrewOutput.

* Encountering issues with callback. Need to test on main. WIP

* working on tests. WIP

* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable

* Fixing missing function. Working on tests.

* WIP. Needing team to review change

* Fixing issues brought about by merge

* WIP: need to fix json encoder

* WIP need to fix encoder

* WIP

* WIP: replay working with async. need to add tests

* Implement major fixes from yesterdays group conversation. Now working on tests.

* The majority of tasks are working now. Need to fix converter class

* Fix final failing test

* Fix linting and type-checker issues

* Add more tests to fully test CrewOutput and TaskOutput changes

* Add in validation for async cannot depend on other async tasks.

* WIP: working replay feat fixing inputs, need tests

* WIP: core logic of seq and heir for executing tasks added into one

* Update validators and tests

* better logic for seq and hier

* replay working for both seq and hier just need tests

* fixed context

* added cli command + code cleanup TODO: need better refactoring

* refactoring for cleaner code

* added better tests

* removed todo comments and fixed some tests

* fix logging now all tests should pass

* cleaner code

* ensure replay is delcared when replaying specific tasks

* ensure hierarchical works

* better typing for stored_outputs and separated task_output_handler

* added better tests

* added replay feature to crew docs

* easier cli command name

* fixing changes

* using sqllite instead of .json file for logging previous task_outputs

* tools fix

* added to docs and fixed tests

* fixed .db

* fixed docs and removed unneeded comments

* separating ltm and replay db

* fixed printing colors

* added how to doc

---------

Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-07-15 17:14:10 -03:00
Gui Vieira
7696b45fc3 Fix tool usage (#925)
* Fix tool usage

* new tests

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 17:13:35 -03:00
Brandon Hancock
641921eb6c capture result from recursive call 2024-07-15 13:59:58 -04:00
Brandon Hancock
a02d2fb93e Add return statement to recursive call 2024-07-15 13:40:51 -04:00
Gui Vieira
b93632a53a [DO NOT MERGE] Provide inputs on crew creation (#898)
* Provide inputs on crew creation

* Better naming

* Add crew id and task index to tasks

* Fix type again
2024-07-15 09:00:02 -03:00
Eduardo Chiarotti
09938641cd feat: add max retry limit to agent execution (#899)
* feat: add max retry limit to agent execution

* feat: add test to max retry limit feature

* feat: add code execution docstring

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 08:58:50 -03:00
Brandon Hancock (bhancock_ai)
7acf0b2107 Feature/use converter instead of manually trimming (#894)
* Exploring output being passed to tool selector to see if we can better format data

* WIP. Adding JSON repair functionality

* Almost done implementing JSON repair. Testing fixes vs current base case.

* More action cleanup with additional tests

* WIP. Trying to figure out what is going on with tool descriptions

* Update tool description generation

* WIP. Trying to find out what is causing the tools to duplicate

* Replacing tools properly instead of duplicating them accidentally

* Fixing issues for MR

* Update dependencies for JSON_REPAIR

* More cleaning up pull request

* preppering for call

* Fix type-checking issues

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 08:53:41 -03:00
OP (oppenheimer)
4eb4073661 Add Groq - OpenAI Compatible API - details (#934) 2024-07-14 16:11:54 -03:00
Brandon Hancock (bhancock_ai)
7b53457ef3 Feature/kickoff consistent output (#847)
* Cleaned up task execution to now have separate paths for async and sync execution. Updating all kickoff functions to return CrewOutput. WIP. Waiting for Joao feedback on async task execution with task_output

* Consistently storing async and sync output for context

* outline tests I need to create going forward

* Major rehaul of TaskOutput and CrewOutput. Updated all tests to work with new change. Need to add in a few final tricky async tests and add a few more to verify output types on TaskOutput and CrewOutput.

* Encountering issues with callback. Need to test on main. WIP

* working on tests. WIP

* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable

* Fixing missing function. Working on tests.

* WIP. Needing team to review change

* Fixing issues brought about by merge

* WIP

* Implement major fixes from yesterdays group conversation. Now working on tests.

* The majority of tasks are working now. Need to fix converter class

* Fix final failing test

* Fix linting and type-checker issues

* Add more tests to fully test CrewOutput and TaskOutput changes

* Add in validation for async cannot depend on other async tasks.

* Update validators and tests
2024-07-11 00:35:02 -03:00
João Moura
691b094a40 adding new docs 2024-07-08 03:15:14 -04:00
prime-computing-lab
68e9e54c88 Update MDXSearchTool.md (#745)
description fixed to markdown language instead of marketing search
2024-07-08 02:21:00 -03:00
João Moura
d0d99125c4 updating crewAI-tools verison 2024-07-08 01:17:22 -04:00
Taleb
129000d01f Performed spell check across most of code base (#882)
* Performed spell check across the entire documentation

Thank you once again!

* Performed spell check across the most of code base
Folders been checked:
- agents
- cli
- memory
- project
- tasks
- telemetry
- tools
- translations
2024-07-07 13:00:05 -03:00
WellyngtonF
47f9d026dd passing cloned agents when copying context (#885) 2024-07-07 12:58:38 -03:00
Gui Vieira
b75b0b5552 Emit task created (#875)
* Emit task created

* Limit data to shared crews
2024-07-07 12:58:24 -03:00
João Moura
3dd6249f1e TYPO 2024-07-06 20:03:54 -04:00
João Moura
8451113039 new docs 2024-07-06 16:32:00 -04:00
João Moura
a79b216875 preparing new version 2024-07-06 12:26:41 -04:00
João Moura
52217c2f63 updating dependencies and fixing tests (#878) 2024-07-06 02:14:52 -03:00
Eelke van den Bos
7edacf6e24 Add converter_cls option to Task (#800)
* Add converter_cls option to Task

Fixes #799

* Update task_test.py

* Update task.py

* Update task.py

* Update task_test.py

* Update task.py

* Update task.py

* Update task.py

* Update task.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-06 02:01:39 -03:00
João Moura
58558a1950 TYPO 2024-07-06 00:34:50 -04:00
Ikko Eltociear Ashimine
1607c85ae5 chore: fix typo (#810)
* chore: update converter.py

attemps -> attempts

* chore: update tool_usage.py

attemps -> attempts
2024-07-06 01:33:48 -03:00
Alex Brinsmead
a6ff342948 Fix incorrect definition of RAG in GithubTool docs (#864) 2024-07-06 01:31:51 -03:00
Taleb
d2eb54ebf8 Performed spell check across the entire documentation (#872)
Thank you once again!
2024-07-06 01:30:40 -03:00
Eduardo Chiarotti
a41bd18599 Fix/async tasks (#877)
* fix: async tasks calls

* fix: some issue along with some type check errors

* fix: some issue along with some type check errors

* fix: async test
2024-07-06 01:30:07 -03:00
Eduardo Chiarotti
bb64c80964 fix: Fix tests (#873)
* fix: call asserts

* fix: test_increment_tool_errors

* fix: test_increment_delegations_for_sequential_process

* fix: test_increment_delegations_for_hierarchical_process

* fix: test_code_execution_flag_adds_code_tool_upon_kickoff

* fix: test_tool_usage_information_is_appended_to_agent

* fix: try to fix test_crew_full_output

* fix: try to fix test_crew_full_output

* fix: test remove vcr to test crew_test test

* fix: comment test to see if ci passes

* fix: comment test to see if ci passes

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test new approach

* fix: comment funciont not working in CI

* fix: github python version

* fix: remove need of vcr

* fix: fix and add comments for all type checking errors
2024-07-05 09:06:56 -03:00
109 changed files with 307154 additions and 11459 deletions

View File

@@ -19,7 +19,7 @@ jobs:
- name: Setup Python
uses: actions/setup-python@v4
with:
python-version: "3.10"
python-version: "3.11.9"
- name: Install Requirements
run: |
@@ -28,4 +28,4 @@ jobs:
poetry install
- name: Run tests
run: poetry run pytest tests
run: poetry run pytest

3
.gitignore vendored
View File

@@ -14,4 +14,5 @@ test.py
rc-tests/*
*.pkl
temp/*
.vscode/*
.vscode/*
crew_tasks_output.json

View File

@@ -4,36 +4,38 @@ description: Understanding and utilizing crews in the crewAI framework with comp
---
## What is a Crew?
A crew in crewAI represents a collaborative group of agents working together to achieve a set of tasks. Each crew defines the strategy for task execution, agent collaboration, and the overall workflow.
## Crew Attributes
| Attribute | Parameters | Description |
| :-------------------------- | :------------------ | :------------------------------------------------------------------------------------------------------- |
| **Tasks** | `tasks` | A list of tasks assigned to the crew. |
| **Agents** | `agents` | A list of agents that are part of the crew. |
| **Process** *(optional)* | `process` | The process flow (e.g., sequential, hierarchical) the crew follows. |
| **Verbose** *(optional)* | `verbose` | The verbosity level for logging during execution. |
| **Manager LLM** *(optional)*| `manager_llm` | The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
| **Function Calling LLM** *(optional)* | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
| **Config** *(optional)* | `config` | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
| **Max RPM** *(optional)* | `max_rpm` | Maximum requests per minute the crew adheres to during execution. |
| **Language** *(optional)* | `language` | Language used for the crew, defaults to English. |
| **Language File** *(optional)* | `language_file` | Path to the language file to be used for the crew. |
| **Memory** *(optional)* | `memory` | Utilized for storing execution memories (short-term, long-term, entity memory). |
| **Cache** *(optional)* | `cache` | Specifies whether to use a cache for storing the results of tools' execution. |
| **Embedder** *(optional)* | `embedder` | Configuration for the embedder to be used by the crew. Mostly used by memory for now. |
| **Full Output** *(optional)*| `full_output` | Whether the crew should return the full output with all tasks outputs or just the final output. |
| **Step Callback** *(optional)* | `step_callback` | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
| **Task Callback** *(optional)* | `task_callback` | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
| **Share Crew** *(optional)* | `share_crew` | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
| **Output Log File** *(optional)* | `output_log_file` | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
| **Manager Agent** *(optional)* | `manager_agent` | `manager` sets a custom agent that will be used as a manager. |
| **Manager Callbacks** *(optional)* | `manager_callbacks` | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
| **Prompt File** *(optional)* | `prompt_file` | Path to the prompt JSON file to be used for the crew. |
| Attribute | Parameters | Description |
| :------------------------------------ | :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Tasks** | `tasks` | A list of tasks assigned to the crew. |
| **Agents** | `agents` | A list of agents that are part of the crew. |
| **Process** _(optional)_ | `process` | The process flow (e.g., sequential, hierarchical) the crew follows. |
| **Verbose** _(optional)_ | `verbose` | The verbosity level for logging during execution. |
| **Manager LLM** _(optional)_ | `manager_llm` | The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
| **Function Calling LLM** _(optional)_ | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
| **Config** _(optional)_ | `config` | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
| **Max RPM** _(optional)_ | `max_rpm` | Maximum requests per minute the crew adheres to during execution. |
| **Language** _(optional)_ | `language` | Language used for the crew, defaults to English. |
| **Language File** _(optional)_ | `language_file` | Path to the language file to be used for the crew. |
| **Memory** _(optional)_ | `memory` | Utilized for storing execution memories (short-term, long-term, entity memory). |
| **Cache** _(optional)_ | `cache` | Specifies whether to use a cache for storing the results of tools' execution. |
| **Embedder** _(optional)_ | `embedder` | Configuration for the embedder to be used by the crew. Mostly used by memory for now. |
| **Full Output** _(optional)_ | `full_output` | Whether the crew should return the full output with all tasks outputs or just the final output. |
| **Step Callback** _(optional)_ | `step_callback` | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
| **Task Callback** _(optional)_ | `task_callback` | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
| **Share Crew** _(optional)_ | `share_crew` | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
| **Output Log File** _(optional)_ | `output_log_file` | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
| **Manager Agent** _(optional)_ | `manager_agent` | `manager` sets a custom agent that will be used as a manager. |
| **Manager Callbacks** _(optional)_ | `manager_callbacks` | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
| **Prompt File** _(optional)_ | `prompt_file` | Path to the prompt JSON file to be used for the crew. |
| **Planning** *(optional)* | `planning` | Adds planning ability to the Crew. When activated before each Crew iteration, all Crew data is sent to an AgentPlanner that will plan the tasks and this plan will be added to each task description.
!!! note "Crew Max RPM"
The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
## Creating a Crew
@@ -44,6 +46,12 @@ When assembling a crew, you combine agents with complementary roles and tools, a
```python
from crewai import Crew, Agent, Task, Process
from langchain_community.tools import DuckDuckGoSearchRun
from crewai_tools import tool
@tool('DuckDuckGoSearch')
def search(search_query: str):
"""Search the web for information on a given topic"""
return DuckDuckGoSearchRun().run(search_query)
# Define agents with specific roles and tools
researcher = Agent(
@@ -54,7 +62,7 @@ researcher = Agent(
to the business.
You're currently working on a project to analyze the
trends and innovations in the space of artificial intelligence.""",
tools=[DuckDuckGoSearchRun()]
tools=[search]
)
writer = Agent(
@@ -89,6 +97,57 @@ my_crew = Crew(
)
```
## Crew Output
!!! note "Understanding Crew Outputs"
The output of a crew in the crewAI framework is encapsulated within the `CrewOutput` class.
This class provides a structured way to access results of the crew's execution, including various formats such as raw strings, JSON, and Pydantic models.
The `CrewOutput` includes the results from the final task output, token usage, and individual task outputs.
### Crew Output Attributes
| Attribute | Parameters | Type | Description |
| :--------------- | :------------- | :------------------------- | :--------------------------------------------------------------------------------------------------- |
| **Raw** | `raw` | `str` | The raw output of the crew. This is the default format for the output. |
| **Pydantic** | `pydantic` | `Optional[BaseModel]` | A Pydantic model object representing the structured output of the crew. |
| **JSON Dict** | `json_dict` | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the crew. |
| **Tasks Output** | `tasks_output` | `List[TaskOutput]` | A list of `TaskOutput` objects, each representing the output of a task in the crew. |
| **Token Usage** | `token_usage` | `Dict[str, Any]` | A summary of token usage, providing insights into the language model's performance during execution. |
### Crew Output Methods and Properties
| Method/Property | Description |
| :-------------- | :------------------------------------------------------------------------------------------------ |
| **json** | Returns the JSON string representation of the crew output if the output format is JSON. |
| **to_dict** | Converts the JSON and Pydantic outputs to a dictionary. |
| \***\*str\*\*** | Returns the string representation of the crew output, prioritizing Pydantic, then JSON, then raw. |
### Accessing Crew Outputs
Once a crew has been executed, its output can be accessed through the `output` attribute of the `Crew` object. The `CrewOutput` class provides various ways to interact with and present this output.
#### Example
```python
# Example crew execution
crew = Crew(
agents=[research_agent, writer_agent],
tasks=[research_task, write_article_task],
verbose=2
)
result = crew.kickoff()
# Accessing the crew output
print(f"Raw Output: {crew_output.raw}")
if crew_output.json_dict:
print(f"JSON Output: {json.dumps(crew_output.json_dict, indent=2)}")
if crew_output.pydantic:
print(f"Pydantic Output: {crew_output.pydantic}")
print(f"Tasks Output: {crew_output.tasks_output}")
print(f"Token Usage: {crew_output.token_usage}")
```
## Memory Utilization
Crews can utilize memory (short-term, long-term, and entity memory) to enhance their execution and learning over time. This feature allows crews to store and recall execution memories, aiding in decision-making and task execution strategies.
@@ -156,3 +215,32 @@ for async_result in async_results:
```
These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs
### Replaying from specific task:
You can now replay from a specific task using our cli command replay.
The replay_from_tasks feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t <task_id>`, you can specify the `task_id` for the replay process.
Kickoffs will now save the latest kickoffs returned task outputs locally for you to be able to replay from.
### Replaying from specific task Using the CLI
To use the replay feature, follow these steps:
1. Open your terminal or command prompt.
2. Navigate to the directory where your CrewAI project is located.
3. Run the following command:
To view latest kickoff task_ids use:
```shell
crewai log-tasks-outputs
```
```shell
crewai replay -t <task_id>
```
These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.

View File

@@ -12,7 +12,7 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
| Component | Description |
| :------------------- | :----------------------------------------------------------- |
| **Short-Term Memory**| Temporarily stores recent interactions and outcomes, enabling agents to recall and utilize information relevant to their current context during the current executions. |
| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remeber what they did right and wrong across multiple executions |
| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remember what they did right and wrong across multiple executions |
| **Entity Memory** | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. |
| **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
@@ -29,6 +29,11 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
When configuring a crew, you can enable and customize each memory component to suit the crew's objectives and the nature of tasks it will perform.
By default, the memory system is disabled, and you can ensure it is active by setting `memory=True` in the crew configuration. The memory will use OpenAI Embeddings by default, but you can change it by setting `embedder` to a different model.
The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG using EmbedChain package.
The **Long-Term Memory** uses SQLLite3 to store task results. Currently, there is no way to override these storage implementations.
The data storage files are saved into a platform specific location found using the appdirs package
and the name of the project which can be overridden using the **CREWAI_STORAGE_DIR** environment variable.
### Example: Configuring Memory for a Crew
```python
@@ -161,10 +166,43 @@ my_crew = Crew(
)
```
### Resetting Memory
```sh
crewai reset_memories [OPTIONS]
```
#### Resetting Memory Options
- **`-l, --long`**
- **Description:** Reset LONG TERM memory.
- **Type:** Flag (boolean)
- **Default:** False
- **`-s, --short`**
- **Description:** Reset SHORT TERM memory.
- **Type:** Flag (boolean)
- **Default:** False
- **`-e, --entities`**
- **Description:** Reset ENTITIES memory.
- **Type:** Flag (boolean)
- **Default:** False
- **`-k, --kickoff-outputs`**
- **Description:** Reset LATEST KICKOFF TASK OUTPUTS.
- **Type:** Flag (boolean)
- **Default:** False
- **`-a, --all`**
- **Description:** Reset ALL memories.
- **Type:** Flag (boolean)
- **Default:** False
## Benefits of Using crewAI's Memory System
- **Adaptive Learning:** Crews become more efficient over time, adapting to new information and refining their approach to tasks.
- **Enhanced Personalization:** Memory enables agents to remember user preferences and historical interactions, leading to personalized experiences.
- **Improved Problem Solving:** Access to a rich memory store aids agents in making more informed decisions, drawing on past learnings and contextual insights.
## Getting Started
Integrating crewAI's memory system into your projects is straightforward. By leveraging the provided memory components and configurations, you can quickly empower your agents with the ability to remember, reason, and learn from their interactions, unlocking new levels of intelligence and capability.
Integrating crewAI's memory system into your projects is straightforward. By leveraging the provided memory components and configurations, you can quickly empower your agents with the ability to remember, reason, and learn from their interactions, unlocking new levels of intelligence and capability.

View File

@@ -0,0 +1,119 @@
---
title: crewAI Planning
description: Learn how to add planning to your crewAI Crew and improve their performance.
---
## Introduction
The planning feature in CrewAI allows you to add planning capability to your crew. When enabled, before each Crew iteration, all Crew information is sent to an AgentPlanner that will plan the tasks step by step, and this plan will be added to each task description.
### Using the Planning Feature
Getting started with the planning feature is very easy, the only step required is to add `planning=True` to your Crew:
```python
from crewai import Crew, Agent, Task, Process
# Assemble your crew with planning capabilities
my_crew = Crew(
agents=self.agents,
tasks=self.tasks,
process=Process.sequential,
planning=True,
)
```
From this point on, your crew will have planning enabled, and the tasks will be planned before each iteration.
### Example
When running the base case example, you will see something like the following output, which represents the output of the AgentPlanner responsible for creating the step-by-step logic to add to the Agents tasks.
```bash
[2024-07-15 16:49:11][INFO]: Planning the crew execution
**Step-by-Step Plan for Task Execution**
**Task Number 1: Conduct a thorough research about AI LLMs**
**Agent:** AI LLMs Senior Data Researcher
**Agent Goal:** Uncover cutting-edge developments in AI LLMs
**Task Expected Output:** A list with 10 bullet points of the most relevant information about AI LLMs
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Define Research Scope:**
- Determine the specific areas of AI LLMs to focus on, such as advancements in architecture, use cases, ethical considerations, and performance metrics.
2. **Identify Reliable Sources:**
- List reputable sources for AI research, including academic journals, industry reports, conferences (e.g., NeurIPS, ACL), AI research labs (e.g., OpenAI, Google AI), and online databases (e.g., IEEE Xplore, arXiv).
3. **Collect Data:**
- Search for the latest papers, articles, and reports published in 2023 and early 2024.
- Use keywords like "Large Language Models 2024", "AI LLM advancements", "AI ethics 2024", etc.
4. **Analyze Findings:**
- Read and summarize the key points from each source.
- Highlight new techniques, models, and applications introduced in the past year.
5. **Organize Information:**
- Categorize the information into relevant topics (e.g., new architectures, ethical implications, real-world applications).
- Ensure each bullet point is concise but informative.
6. **Create the List:**
- Compile the 10 most relevant pieces of information into a bullet point list.
- Review the list to ensure clarity and relevance.
**Expected Output:**
A list with 10 bullet points of the most relevant information about AI LLMs.
---
**Task Number 2: Review the context you got and expand each topic into a full section for a report**
**Agent:** AI LLMs Reporting Analyst
**Agent Goal:** Create detailed reports based on AI LLMs data analysis and research findings
**Task Expected Output:** A fully fledge report with the main topics, each with a full section of information. Formatted as markdown without '```'
**Task Tools:** None specified
**Agent Tools:** None specified
**Step-by-Step Plan:**
1. **Review the Bullet Points:**
- Carefully read through the list of 10 bullet points provided by the AI LLMs Senior Data Researcher.
2. **Outline the Report:**
- Create an outline with each bullet point as a main section heading.
- Plan sub-sections under each main heading to cover different aspects of the topic.
3. **Research Further Details:**
- For each bullet point, conduct additional research if necessary to gather more detailed information.
- Look for case studies, examples, and statistical data to support each section.
4. **Write Detailed Sections:**
- Expand each bullet point into a comprehensive section.
- Ensure each section includes an introduction, detailed explanation, examples, and a conclusion.
- Use markdown formatting for headings, subheadings, lists, and emphasis.
5. **Review and Edit:**
- Proofread the report for clarity, coherence, and correctness.
- Make sure the report flows logically from one section to the next.
- Format the report according to markdown standards.
6. **Finalize the Report:**
- Ensure the report is complete with all sections expanded and detailed.
- Double-check formatting and make any necessary adjustments.
**Expected Output:**
A fully-fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'.
---
```

View File

@@ -4,27 +4,29 @@ description: Detailed guide on managing and creating tasks within the crewAI fra
---
## Overview of a Task
!!! note "What is a Task?"
In the crewAI framework, tasks are specific assignments completed by agents. They provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
In the crewAI framework, tasks are specific assignments completed by agents. They provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
Tasks within crewAI can be collaborative, requiring multiple agents to work together. This is managed through the task properties and orchestrated by the Crew's process, enhancing teamwork and efficiency.
## Task Attributes
| Attribute | Parameters | Description |
| :----------------------| :------------------- | :-------------------------------------------------------------------------------------------- |
| **Description** | `description` | A clear, concise statement of what the task entails. |
| **Agent** | `agent` | The agent responsible for the task, assigned either directly or by the crew's process. |
| **Expected Output** | `expected_output` | A detailed description of what the task's completion looks like. |
| **Tools** *(optional)* | `tools` | The functions or capabilities the agent can utilize to perform the task. |
| **Async Execution** *(optional)* | `async_execution` | If set, the task executes asynchronously, allowing progression without waiting for completion.|
| **Context** *(optional)* | `context` | Specifies tasks whose outputs are used as context for this task. |
| **Config** *(optional)* | `config` | Additional configuration details for the agent executing the task, allowing further customization. |
| **Output JSON** *(optional)* | `output_json` | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set. |
| **Output Pydantic** *(optional)* | `output_pydantic` | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
| **Output File** *(optional)* | `output_file` | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
| **Callback** *(optional)* | `callback` | A Python callable that is executed with the task's output upon completion. |
| **Human Input** *(optional)* | `human_input` | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
| Attribute | Parameters | Description |
| :------------------------------- | :---------------- | :------------------------------------------------------------------------------------------------------------------- |
| **Description** | `description` | A clear, concise statement of what the task entails. |
| **Agent** | `agent` | The agent responsible for the task, assigned either directly or by the crew's process. |
| **Expected Output** | `expected_output` | A detailed description of what the task's completion looks like. |
| **Tools** _(optional)_ | `tools` | The functions or capabilities the agent can utilize to perform the task. |
| **Async Execution** _(optional)_ | `async_execution` | If set, the task executes asynchronously, allowing progression without waiting for completion. |
| **Context** _(optional)_ | `context` | Specifies tasks whose outputs are used as context for this task. |
| **Config** _(optional)_ | `config` | Additional configuration details for the agent executing the task, allowing further customization. |
| **Output JSON** _(optional)_ | `output_json` | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set. |
| **Output Pydantic** _(optional)_ | `output_pydantic` | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
| **Output File** _(optional)_ | `output_file` | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
| **Output** _(optional)_ | `output` | The output of the task, containing the raw, JSON, and Pydantic output plus additional details. |
| **Callback** _(optional)_ | `callback` | A Python callable that is executed with the task's output upon completion. |
| **Human Input** _(optional)_ | `human_input` | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
## Creating a Task
@@ -35,12 +37,75 @@ from crewai import Task
task = Task(
description='Find and summarize the latest and most relevant news on AI',
agent=sales_agent
agent=sales_agent,
expected_output='A bullet list summary of the top 5 most important AI news',
)
```
!!! note "Task Assignment"
Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
## Task Output
!!! note "Understanding Task Outputs"
The output of a task in the crewAI framework is encapsulated within the `TaskOutput` class. This class provides a structured way to access results of a task, including various formats such as raw strings, JSON, and Pydantic models.
By default, the `TaskOutput` will only include the `raw` output. A `TaskOutput` will only include the `pydantic` or `json_dict` output if the original `Task` object was configured with `output_pydantic` or `output_json`, respectively.
### Task Output Attributes
| Attribute | Parameters | Type | Description |
| :---------------- | :-------------- | :------------------------- | :------------------------------------------------------------------------------------------------- |
| **Description** | `description` | `str` | A brief description of the task. |
| **Summary** | `summary` | `Optional[str]` | A short summary of the task, auto-generated from the description. |
| **Raw** | `raw` | `str` | The raw output of the task. This is the default format for the output. |
| **Pydantic** | `pydantic` | `Optional[BaseModel]` | A Pydantic model object representing the structured output of the task. |
| **JSON Dict** | `json_dict` | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the task. |
| **Agent** | `agent` | `str` | The agent that executed the task. |
| **Output Format** | `output_format` | `OutputFormat` | The format of the task output, with options including RAW, JSON, and Pydantic. The default is RAW. |
### Task Output Methods and Properties
| Method/Property | Description |
| :-------------- | :------------------------------------------------------------------------------------------------ |
| **json** | Returns the JSON string representation of the task output if the output format is JSON. |
| **to_dict** | Converts the JSON and Pydantic outputs to a dictionary. |
| \***\*str\*\*** | Returns the string representation of the task output, prioritizing Pydantic, then JSON, then raw. |
### Accessing Task Outputs
Once a task has been executed, its output can be accessed through the `output` attribute of the `Task` object. The `TaskOutput` class provides various ways to interact with and present this output.
#### Example
```python
# Example task
task = Task(
description='Find and summarize the latest AI news',
expected_output='A bullet list summary of the top 5 most important AI news',
agent=research_agent,
tools=[search_tool]
)
# Execute the crew
crew = Crew(
agents=[research_agent],
tasks=[task],
verbose=2
)
result = crew.kickoff()
# Accessing the task output
task_output = task.output
print(f"Task Description: {task_output.description}")
print(f"Task Summary: {task_output.summary}")
print(f"Raw Output: {task_output.raw}")
if task_output.json_dict:
print(f"JSON Output: {json.dumps(task_output.json_dict, indent=2)}")
if task_output.pydantic:
print(f"Pydantic Output: {task_output.pydantic}")
```
## Integrating Tools with Tasks

View File

@@ -100,16 +100,24 @@ Here is a list of the available tools and their descriptions:
| Tool | Description |
| :-------------------------- | :-------------------------------------------------------------------------------------------- |
| **BrowserbaseLoadTool** | A tool for interacting with and extracting data from web browsers. |
| **CodeDocsSearchTool** | A RAG tool optimized for searching through code documentation and related technical documents. |
| **CodeInterpreterTool** | A tool for interpreting python code. |
| **ComposioTool** | Enables use of Composio tools. |
| **CSVSearchTool** | A RAG tool designed for searching within CSV files, tailored to handle structured data. |
| **DirectorySearchTool** | A RAG tool for searching within directories, useful for navigating through file systems. |
| **DOCXSearchTool** | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files. |
| **DirectoryReadTool** | Facilitates reading and processing of directory structures and their contents. |
| **EXASearchTool** | A tool designed for performing exhaustive searches across various data sources. |
| **FileReadTool** | Enables reading and extracting data from files, supporting various file formats. |
| **FirecrawlSearchTool** | A tool to search webpages using Firecrawl and return the results. |
| **FirecrawlCrawlWebsiteTool** | A tool for crawling webpages using Firecrawl. |
| **FirecrawlScrapeWebsiteTool** | A tool for scraping webpages url using Firecrawl and returning its contents. |
| **GithubSearchTool** | A RAG tool for searching within GitHub repositories, useful for code and documentation search.|
| **SerperDevTool** | A specialized tool for development purposes, with specific functionalities under development. |
| **TXTSearchTool** | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data. |
| **JSONSearchTool** | A RAG tool designed for searching within JSON files, catering to structured data handling. |
| **LlamaIndexTool** | Enables the use of LlamaIndex tools. |
| **MDXSearchTool** | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation. |
| **PDFSearchTool** | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents. |
| **PGSearchTool** | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
@@ -120,8 +128,6 @@ Here is a list of the available tools and their descriptions:
| **XMLSearchTool** | A RAG tool designed for searching within XML files, suitable for structured data formats. |
| **YoutubeChannelSearchTool**| A RAG tool for searching within YouTube channels, useful for video content analysis. |
| **YoutubeVideoSearchTool** | A RAG tool aimed at searching within YouTube videos, ideal for video data extraction. |
| **BrowserbaseTool** | A tool for interacting with and extracting data from web browsers. |
| **ExaSearchTool** | A tool designed for performing exhaustive searches across various data sources. |
## Creating your own Tools

View File

@@ -0,0 +1,87 @@
---
title: Conditional Tasks
description: Learn how to use conditional tasks in a crewAI kickoff
---
## Introduction
Conditional Tasks in crewAI allow for dynamic workflow adaptation based on the outcomes of previous tasks. This powerful feature enables crews to make decisions and execute tasks selectively, enhancing the flexibility and efficiency of your AI-driven processes.
```python
from typing import List
from pydantic import BaseModel
from crewai import Agent, Crew
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.task import Task
from crewai_tools import SerperDevTool
# Define a condition function for the conditional task
# if false task will be skipped, true, then execute task
def is_data_missing(output: TaskOutput) -> bool:
return len(output.pydantic.events) < 10: # this will skip this task
# Define the agents
data_fetcher_agent = Agent(
role="Data Fetcher",
goal="Fetch data online using Serper tool",
backstory="Backstory 1",
verbose=True,
tools=[SerperDevTool()],
)
data_processor_agent = Agent(
role="Data Processor",
goal="Process fetched data",
backstory="Backstory 2",
verbose=True,
)
summary_generator_agent = Agent(
role="Summary Generator",
goal="Generate summary from fetched data",
backstory="Backstory 3",
verbose=True,
)
class EventOutput(BaseModel):
events: List[str]
task1 = Task(
description="Fetch data about events in San Francisco using Serper tool",
expected_output="List of 10 things to do in SF this week",
agent=data_fetcher_agent,
output_pydantic=EventOutput,
)
conditional_task = ConditionalTask(
description="""
Check if data is missing. If we have less than 10 events,
fetch more events using Serper tool so that
we have a total of 10 events in SF this week..
""",
expected_output="List of 10 Things to do in SF this week ",
condition=is_data_missing,
agent=data_processor_agent,
)
task3 = Task(
description="Generate summary of events in San Francisco from fetched data",
expected_output="summary_generated",
agent=summary_generator_agent,
)
# Create a crew with the tasks
crew = Crew(
agents=[data_fetcher_agent, data_processor_agent, summary_generator_agent],
tasks=[task1, conditional_task, task3],
verbose=2,
)
result = crew.kickoff()
print("results", result)
```

View File

@@ -51,7 +51,7 @@ To optimize tool performance with caching, define custom caching strategies usin
@tool("Tool with Caching")
def cached_tool(argument: str) -> str:
"""Tool functionality description."""
return "Cachable result"
return "Cacheable result"
def my_cache_strategy(arguments: dict, result: str) -> bool:
# Define custom caching logic

View File

@@ -21,14 +21,16 @@ Define your agents with distinct roles, backstories, and enhanced capabilities.
import os
from langchain.llms import OpenAI
from crewai import Agent
from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
from crewai_tools import SerperDevTool, BrowserbaseLoadTool, EXASearchTool
os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
os.environ["SERPER_API_KEY"] = "Your Serper Key"
os.environ["BROWSERBASE_API_KEY"] = "Your BrowserBase Key"
os.environ["BROWSERBASE_PROJECT_ID"] = "Your BrowserBase Project Id"
search_tool = SerperDevTool()
browser_tool = BrowserbaseTool()
exa_search_tool = ExaSearchTool()
browser_tool = BrowserbaseLoadTool()
exa_search_tool = EXASearchTool()
# Creating a senior researcher agent with advanced configurations
researcher = Agent(
@@ -79,5 +81,4 @@ manager = Agent(
1. `allow_code_execution`: Enable or disable code execution capabilities for the agent (default is False).
2. `max_execution_time`: Set a maximum execution time (in seconds) for the agent to complete a task.
3. `function_calling_llm`: Specify a separate language model for function calling.
4
3. `function_calling_llm`: Specify a separate language model for function calling.

View File

@@ -0,0 +1,31 @@
---
title: Forcing Tool Output as Result
description: Learn how to force tool output as the result in of an Agent's task in crewAI.
---
## Introduction
In CrewAI, you can force the output of a tool as the result of an agent's task. This feature is useful when you want to ensure that the tool output is captured and returned as the task result, and avoid the agent modifying the output during the task execution.
## Forcing Tool Output as Result
To force the tool output as the result of an agent's task, you can set the `force_tool_output` parameter to `True` when creating the task. This parameter ensures that the tool output is captured and returned as the task result, without any modifications by the agent.
Here's an example of how to force the tool output as the result of an agent's task:
```python
# ...
# Define a custom tool that returns the result as the answer
coding_agent =Agent(
role="Data Scientist",
goal="Product amazing resports on AI",
backstory="You work with data and AI",
tools=[MyCustomTool(result_as_answer=True)],
)
# ...
```
### Workflow in Action
1. **Task Execution**: The agent executes the task using the tool provided.
2. **Tool Output**: The tool generates the output, which is captured as the task result.
3. **Agent Interaction**: The agent my reflect and take learnings from the tool but the output is not modified.
4. **Result Return**: The tool output is returned as the task result without any modifications.

View File

@@ -127,7 +127,7 @@ llm = HuggingFaceHub(
```
## OpenAI Compatible API Endpoints
Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, and Mistral AI.
Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
### Configuration Examples
#### FastChat
@@ -144,6 +144,13 @@ OPENAI_API_BASE="http://localhost:1234/v1"
OPENAI_API_KEY="lm-studio"
```
#### Groq API
```sh
OPENAI_API_KEY=your-groq-api-key
OPENAI_MODEL_NAME='llama3-8b-8192'
OPENAI_API_BASE=https://api.groq.com/openai/v1
```
#### Mistral API
```sh
OPENAI_API_KEY=your-mistral-api-key
@@ -211,4 +218,4 @@ azure_agent = Agent(
```
## Conclusion
Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.
Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

View File

@@ -0,0 +1,49 @@
---
title: Replay Tasks from Latest Crew Kickoff
description: Replay tasks from the latest crew.kickoff(...)
---
## Introduction
CrewAI provides the ability to replay from a task specified from the latest crew kickoff. This feature is particularly useful when you've finished a kickoff and may want to retry certain tasks or don't need to refetch data over and your agents already have the context saved from the kickoff execution so you just need to replay the tasks you want to.
## Note:
You must run `crew.kickoff()` before you can replay a task. Currently, only the latest kickoff is supported, so if you use `kickoff_for_each`, it will only allow you to replay from the most recent crew run.
Here's an example of how to replay from a task:
### Replaying from specific task Using the CLI
To use the replay feature, follow these steps:
1. Open your terminal or command prompt.
2. Navigate to the directory where your CrewAI project is located.
3. Run the following command:
To view latest kickoff task_ids use:
```shell
crewai log-tasks-outputs
```
Once you have your task_id to replay from use:
```shell
crewai replay -t <task_id>
```
### Replaying from a task Programmatically
To replay from a task programmatically, use the following steps:
1. Specify the task_id and input parameters for the replay process.
2. Execute the replay command within a try-except block to handle potential errors.
```python
def replay_from_task():
"""
Replay the crew execution from a specific task.
"""
task_id = '<task_id>'
inputs = {"topic": "CrewAI Training"} # this is optional, you can pass in the inputs you want to replay otherwise uses the previous kickoffs inputs
try:
YourCrewName_Crew().crew().replay_from_task(task_id=task_id, inputs=inputs)
except Exception as e:
raise Exception(f"An error occurred while replaying the crew: {e}")

View File

@@ -0,0 +1,137 @@
---
title: Starting a New CrewAI Project
description: A comprehensive guide to starting a new CrewAI project, including the latest updates and project setup methods.
---
# Starting Your CrewAI Project
Welcome to the ultimate guide for starting a new CrewAI project. This document will walk you through the steps to create, customize, and run your CrewAI project, ensuring you have everything you need to get started.
## Prerequisites
We assume you have already installed CrewAI. If not, please refer to the [installation guide](https://docs.crewai.com/how-to/Installing-CrewAI/) to install CrewAI and its dependencies.
## Creating a New Project
To create a new project, run the following CLI command:
```shell
$ crewai create my_project
```
This command will create a new project folder with the following structure:
```shell
my_project/
├── .gitignore
├── pyproject.toml
├── README.md
└── src/
└── my_project/
├── __init__.py
├── main.py
├── crew.py
├── tools/
│ ├── custom_tool.py
│ └── __init__.py
└── config/
├── agents.yaml
└── tasks.yaml
```
You can now start developing your project by editing the files in the `src/my_project` folder. The `main.py` file is the entry point of your project, and the `crew.py` file is where you define your agents and tasks.
## Customizing Your Project
To customize your project, you can:
- Modify `src/my_project/config/agents.yaml` to define your agents.
- Modify `src/my_project/config/tasks.yaml` to define your tasks.
- Modify `src/my_project/crew.py` to add your own logic, tools, and specific arguments.
- Modify `src/my_project/main.py` to add custom inputs for your agents and tasks.
- Add your environment variables into the `.env` file.
### Example: Defining Agents and Tasks
#### agents.yaml
```yaml
researcher:
role: >
Job Candidate Researcher
goal: >
Find potential candidates for the job
backstory: >
You are adept at finding the right candidates by exploring various online
resources. Your skill in identifying suitable candidates ensures the best
match for job positions.
```
#### tasks.yaml
```yaml
research_candidates_task:
description: >
Conduct thorough research to find potential candidates for the specified job.
Utilize various online resources and databases to gather a comprehensive list of potential candidates.
Ensure that the candidates meet the job requirements provided.
Job Requirements:
{job_requirements}
expected_output: >
A list of 10 potential candidates with their contact information and brief profiles highlighting their suitability.
```
## Installing Dependencies
To install the dependencies for your project, you can use Poetry. First, navigate to your project directory:
```shell
$ cd my_project
$ poetry lock
$ poetry install
```
This will install the dependencies specified in the `pyproject.toml` file.
## Interpolating Variables
Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{variable}` will be replaced by the value of the variable in the `main.py` file.
#### agents.yaml
```yaml
research_task:
description: >
Conduct a thorough research about the customer and competitors in the context
of {customer_domain}.
Make sure you find any interesting and relevant information given the
current year is 2024.
expected_output: >
A complete report on the customer and their customers and competitors,
including their demographics, preferences, market positioning and audience engagement.
```
#### main.py
```python
# main.py
def run():
inputs = {
"customer_domain": "crewai.com"
}
MyProjectCrew(inputs).crew().kickoff(inputs=inputs)
```
## Running Your Project
To run your project, use the following command:
```shell
$ poetry run my_project
```
This will initialize your crew of AI agents and begin task execution as defined in your configuration in the `main.py` file.
## Deploying Your Project
The easiest way to deploy your crew is through [CrewAI+](https://www.crewai.com/crewaiplus), where you can deploy your crew in a few clicks.

View File

@@ -43,11 +43,21 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
Memory
</a>
</li>
<li>
<a href="./core-concepts/Planning">
Planning
</a>
</li>
</ul>
</div>
<div style="width:30%">
<h2>How-To Guides</h2>
<ul>
<li>
<a href="./how-to/Start-a-New-CrewAI-Project">
Starting Your crewAI Project
</a>
</li>
<li>
<a href="./how-to/Installing-CrewAI">
Installing crewAI
@@ -88,6 +98,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
Coding Agents
</a>
</li>
<li>
<a href="./how-to/Force-Tool-Ouput-as-Result">
Forcing Tool Output as Result
</a>
</li>
<li>
<a href="./how-to/Human-Input-on-Execution">
Human Input on Execution
@@ -103,6 +118,16 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
Kickoff a Crew for a List
</a>
</li>
<li>
<a href="./how-to/Replay-tasks-from-latest-Crew-Kickoff">
Replay from a Task
</a>
</li>
<li>
<a href="./how-to/Conditional-Tasks">
Conditional Tasks
</a>
</li>
<li>
<a href="./how-to/AgentOps-Observability">
Agent Monitoring with AgentOps

View File

@@ -4,7 +4,7 @@
We are still working on improving tools, so there might be unexpected behavior or changes in the future.
## Description
The GithubSearchTool is a Read, Append, and Generate (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
The GithubSearchTool is a Retrieval-Augmented Generation (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
## Installation
To use the GithubSearchTool, first ensure the crewai_tools package is installed in your Python environment:

View File

@@ -4,7 +4,7 @@
The MDXSearchTool is in continuous development. Features may be added or removed, and functionality could change unpredictably as we refine the tool.
## Description
The MDX Search Tool is a component of the `crewai_tools` package aimed at facilitating advanced market data extraction. This tool is invaluable for researchers and analysts seeking quick access to market insights, especially within the AI sector. It simplifies the task of acquiring, interpreting, and organizing market data by interfacing with various data sources.
The MDX Search Tool is a component of the `crewai_tools` package aimed at facilitating advanced markdown language extraction. It enables users to effectively search and extract relevant information from MD files using query-based searches. This tool is invaluable for data analysis, information management, and research tasks, streamlining the process of finding specific information within large document collections.
## Installation
Before using the MDX Search Tool, ensure the `crewai_tools` package is installed. If it is not, you can install it with the following command:
@@ -59,4 +59,4 @@ tool = MDXSearchTool(
),
)
)
```
```

View File

@@ -31,7 +31,7 @@ tool = TXTSearchTool(txt='path/to/text/file.txt')
```
## Arguments
- `txt` (str): **Optinal**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
- `txt` (str): **Optional**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
## Custom model and embeddings

View File

@@ -128,9 +128,11 @@ nav:
- Collaboration: 'core-concepts/Collaboration.md'
- Training: 'core-concepts/Training-Crew.md'
- Memory: 'core-concepts/Memory.md'
- Planning: 'core-concepts/Planning.md'
- Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
- Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
- How to Guides:
- Starting Your crewAI Project: 'how-to/Start-a-New-CrewAI-Project.md'
- Installing CrewAI: 'how-to/Installing-CrewAI.md'
- Getting Started: 'how-to/Creating-a-Crew-and-kick-it-off.md'
- Create Custom Tools: 'how-to/Create-Custom-Tools.md'
@@ -140,9 +142,12 @@ nav:
- Connecting to any LLM: 'how-to/LLM-Connections.md'
- Customizing Agents: 'how-to/Customizing-Agents.md'
- Coding Agents: 'how-to/Coding-Agents.md'
- Forcing Tool Output as Result: 'how-to/Force-Tool-Ouput-as-Result.md'
- Human Input on Execution: 'how-to/Human-Input-on-Execution.md'
- Kickoff a Crew Asynchronously: 'how-to/Kickoff-async.md'
- Kickoff a Crew for a List: 'how-to/Kickoff-for-each.md'
- Replay from a specific task from a kickoff: 'how-to/Replay-tasks-from-latest-Crew-Kickoff.md'
- Conditional Tasks: 'how-to/Conditional-Tasks.md'
- Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
- Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
- Tools Docs:
@@ -178,6 +183,7 @@ nav:
- Landing Page Generator: https://github.com/joaomdmoura/crewAI-examples/tree/main/landing_page_generator"
- Prepare for meetings: https://github.com/joaomdmoura/crewAI-examples/tree/main/prep-for-a-meeting"
- Telemetry: 'telemetry/Telemetry.md'
- Change Log: 'https://github.com/crewAIInc/crewAI/releases'
extra_css:
- stylesheets/output.css

757
poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "crewai"
version = "0.35.8"
version = "0.41.0"
description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
authors = ["Joao Moura <joao@crewai.com>"]
readme = "README.md"
@@ -21,13 +21,14 @@ opentelemetry-sdk = "^1.22.0"
opentelemetry-exporter-otlp-proto-http = "^1.22.0"
instructor = "1.3.3"
regex = "^2023.12.25"
crewai-tools = { version = "^0.4.7", optional = true }
crewai-tools = { version = "^0.4.26", optional = true }
click = "^8.1.7"
python-dotenv = "^1.0.0"
appdirs = "^1.4.4"
jsonref = "^1.1.0"
agentops = { version = "^0.1.9", optional = true }
agentops = { version = "^0.3.0", optional = true }
embedchain = "^0.1.114"
json-repair = "^0.25.2"
[tool.poetry.extras]
tools = ["crewai-tools"]
@@ -45,7 +46,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
mkdocs-material-extensions = "^1.3.1"
pillow = "^10.2.0"
cairosvg = "^2.7.1"
crewai-tools = "^0.4.7"
crewai-tools = "^0.4.26"
[tool.poetry.group.test.dependencies]
pytest = "^8.0.0"

View File

@@ -1,13 +1,14 @@
import os
from inspect import signature
from typing import Any, List, Optional, Tuple
from langchain.agents.agent import RunnableAgent
from langchain.agents.tools import BaseTool
from langchain.agents.tools import tool as LangChainTool
from langchain.tools.render import render_text_description
from langchain_core.agents import AgentAction
from langchain_core.callbacks import BaseCallbackHandler
from langchain_openai import ChatOpenAI
from pydantic import Field, InstanceOf, model_validator
from pydantic import Field, InstanceOf, PrivateAttr, model_validator
from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
from crewai.agents.agent_builder.base_agent import BaseAgent
@@ -20,7 +21,7 @@ from crewai.utilities.training_handler import CrewTrainingHandler
agentops = None
try:
import agentops
import agentops # type: ignore # Name "agentops" already defined on line 21
from agentops import track_agent
except ImportError:
@@ -54,14 +55,17 @@ class Agent(BaseAgent):
tools: Tools at agents disposal
step_callback: Callback to be executed after each step of the agent execution.
callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
allow_code_execution: Enable code execution for the agent.
max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
"""
_times_executed: int = PrivateAttr(default=0)
max_execution_time: Optional[int] = Field(
default=None,
description="Maximum execution time for an agent to execute a task",
)
agent_ops_agent_name: str = None
agent_ops_agent_id: str = None
agent_ops_agent_name: str = None # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
agent_ops_agent_id: str = None # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
cache_handler: InstanceOf[CacheHandler] = Field(
default=None, description="An instance of the CacheHandler class."
)
@@ -96,6 +100,10 @@ class Agent(BaseAgent):
allow_code_execution: Optional[bool] = Field(
default=False, description="Enable code execution for the agent."
)
max_retry_limit: int = Field(
default=2,
description="Maximum number of retries for an agent to execute a task when an error occurs.",
)
def __init__(__pydantic_self__, **data):
config = data.pop("config", {})
@@ -148,8 +156,7 @@ class Agent(BaseAgent):
Output of the agent
"""
if self.tools_handler:
# type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
self.tools_handler.last_used_tool = {}
self.tools_handler.last_used_tool = {} # type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
task_prompt = task.prompt()
@@ -168,14 +175,15 @@ class Agent(BaseAgent):
if memory.strip() != "":
task_prompt += self.i18n.slice("memory").format(memory=memory)
tools = tools or self.tools
# type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
parsed_tools = self._parse_tools(tools or [])
tools = tools or self.tools or []
parsed_tools = self._parse_tools(tools)
self.create_agent_executor(tools=tools)
self.agent_executor.tools = parsed_tools
self.agent_executor.task = task
self.agent_executor.tools_description = render_text_description(parsed_tools)
self.agent_executor.tools_description = self._render_text_description_and_args(
parsed_tools
)
self.agent_executor.tools_names = self.__tools_names(parsed_tools)
if self.crew and self.crew._train:
@@ -183,20 +191,27 @@ class Agent(BaseAgent):
else:
task_prompt = self._use_trained_data(task_prompt=task_prompt)
result = self.agent_executor.invoke(
{
"input": task_prompt,
"tool_names": self.agent_executor.tools_names,
"tools": self.agent_executor.tools_description,
}
)["output"]
try:
result = self.agent_executor.invoke(
{
"input": task_prompt,
"tool_names": self.agent_executor.tools_names,
"tools": self.agent_executor.tools_description,
}
)["output"]
except Exception as e:
self._times_executed += 1
if self._times_executed > self.max_retry_limit:
raise e
result = self.execute_task(task, context, tools)
if self.max_rpm:
self._rpm_controller.stop_rpm_counter()
# If there was any tool in self.tools_results that had result_as_answer
# set to True, return the results of the last tool that had
# result_as_answer set to True
for tool_result in self.tools_results:
for tool_result in self.tools_results: # type: ignore # Item "None" of "list[Any] | None" has no attribute "__iter__" (not iterable)
if tool_result.get("result_as_answer", False):
result = tool_result["result"]
@@ -221,7 +236,7 @@ class Agent(BaseAgent):
Returns:
An instance of the CrewAgentExecutor class.
"""
tools = tools or self.tools
tools = tools or self.tools or []
agent_args = {
"input": lambda x: x["input"],
@@ -300,7 +315,7 @@ class Agent(BaseAgent):
def get_output_converter(self, llm, text, model, instructions):
return Converter(llm=llm, text=text, model=model, instructions=instructions)
def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:
def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]: # type: ignore # Function "langchain_core.tools.tool" is not valid as a type
"""Parse tools to be used for the task."""
tools_list = []
try:
@@ -316,6 +331,7 @@ class Agent(BaseAgent):
tools_list = []
for tool in tools:
tools_list.append(tool)
return tools_list
def _training_handler(self, task_prompt: str) -> str:
@@ -342,6 +358,52 @@ class Agent(BaseAgent):
)
return task_prompt
def _render_text_description(self, tools: List[BaseTool]) -> str:
"""Render the tool name and description in plain text.
Output will be in the format of:
.. code-block:: markdown
search: This tool is used for search
calculator: This tool is used for math
"""
description = "\n".join(
[
f"Tool name: {tool.name}\nTool description:\n{tool.description}"
for tool in tools
]
)
return description
def _render_text_description_and_args(self, tools: List[BaseTool]) -> str:
"""Render the tool name, description, and args in plain text.
Output will be in the format of:
.. code-block:: markdown
search: This tool is used for search, args: {"query": {"type": "string"}}
calculator: This tool is used for math, \
args: {"expression": {"type": "string"}}
"""
tool_strings = []
for tool in tools:
args_schema = str(tool.args)
if hasattr(tool, "func") and tool.func:
sig = signature(tool.func)
description = (
f"Tool Name: {tool.name}{sig}\nTool Description: {tool.description}"
)
else:
description = (
f"Tool Name: {tool.name}\nTool Description: {tool.description}"
)
tool_strings.append(f"{description}\nTool Arguments: {args_schema}")
return "\n".join(tool_strings)
@staticmethod
def __tools_names(tools) -> str:
return ", ".join([t.name for t in tools])

View File

@@ -1,6 +1,7 @@
import uuid
from abc import ABC, abstractmethod
from copy import copy as shallow_copy
from hashlib import md5
from typing import Any, Dict, List, Optional, TypeVar
from pydantic import (
@@ -162,6 +163,11 @@ class BaseAgent(ABC, BaseModel):
self._token_process = TokenProcess()
return self
@property
def key(self):
source = [self.role, self.goal, self.backstory]
return md5("|".join(source).encode()).hexdigest()
@abstractmethod
def execute_task(
self,
@@ -180,7 +186,7 @@ class BaseAgent(ABC, BaseModel):
pass
@abstractmethod
def get_delegation_tools(self, agents: List["BaseAgent"]):
def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[Any]:
"""Set the task tools that init BaseAgenTools class."""
pass
@@ -191,7 +197,7 @@ class BaseAgent(ABC, BaseModel):
"""Get the converter class for the agent to create json/pydantic outputs."""
pass
def copy(self: T) -> T:
def copy(self: T) -> T: # type: ignore # Signature of "copy" incompatible with supertype "BaseModel"
"""Create a deep copy of the Agent."""
exclude = {
"id",

View File

@@ -1,6 +1,8 @@
from abc import ABC, abstractmethod
from typing import List, Optional, Union
from pydantic import BaseModel, Field
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.task import Task
from crewai.utilities import I18N
@@ -22,6 +24,7 @@ class BaseAgentTools(BaseModel, ABC):
is_list = coworker.startswith("[") and coworker.endswith("]")
if is_list:
coworker = coworker[1:-1].split(",")[0]
return coworker
def delegate_work(
@@ -38,11 +41,13 @@ class BaseAgentTools(BaseModel, ABC):
coworker = self._get_coworker(coworker, **kwargs)
return self._execute(coworker, question, context)
def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
def _execute(
self, agent_name: Union[str, None], task: str, context: Union[str, None]
):
"""Execute the command."""
try:
if agent is None:
agent = ""
if agent_name is None:
agent_name = ""
# It is important to remove the quotes from the agent name.
# The reason we have to do this is because less-powerful LLM's
@@ -51,9 +56,9 @@ class BaseAgentTools(BaseModel, ABC):
# {"task": "....", "coworker": "....
# when it should look like this:
# {"task": "....", "coworker": "...."}
agent_name = agent.casefold().replace('"', "").replace("\n", "")
agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
agent = [
agent = [ # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
available_agent
for available_agent in self.agents
if available_agent.role.casefold().replace("\n", "") == agent_name
@@ -73,9 +78,9 @@ class BaseAgentTools(BaseModel, ABC):
)
agent = agent[0]
task = Task(
task_with_assigned_agent = Task( # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
description=task,
agent=agent,
expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
)
return agent.execute_task(task, context)
return agent.execute_task(task_with_assigned_agent, context)

View File

@@ -1,8 +1,7 @@
from abc import ABC, abstractmethod
from typing import Any, Optional
from pydantic import BaseModel, Field, PrivateAttr
from pydantic import BaseModel, Field
class OutputConverter(BaseModel, ABC):
@@ -22,13 +21,12 @@ class OutputConverter(BaseModel, ABC):
max_attempts (int): Maximum number of conversion attempts (default: 3).
"""
_is_gpt: bool = PrivateAttr(default=True)
text: str = Field(description="Text to be converted.")
llm: Any = Field(description="The language model to be used to convert the text.")
model: Any = Field(description="The model to be used to convert the text.")
instructions: str = Field(description="Conversion instructions to the LLM.")
max_attempts: Optional[int] = Field(
description="Max number of attemps to try to get the output formated.",
description="Max number of attempts to try to get the output formatted.",
default=3,
)
@@ -42,7 +40,8 @@ class OutputConverter(BaseModel, ABC):
"""Convert text to json."""
pass
@property
@abstractmethod
def _is_gpt(self, llm):
def is_gpt(self) -> bool:
"""Return if llm provided is of gpt from openai."""
pass

View File

@@ -1,33 +1,22 @@
import threading
import time
from typing import (
Any,
Dict,
Iterator,
List,
Optional,
Tuple,
Union,
)
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
from langchain.agents import AgentExecutor
from langchain.agents.agent import ExceptionTool
from langchain.callbacks.manager import CallbackManagerForChainRun
from langchain_core.agents import AgentAction, AgentFinish, AgentStep
from langchain_core.exceptions import OutputParserException
from langchain_core.tools import BaseTool
from langchain_core.utils.input import get_color_mapping
from pydantic import InstanceOf
from crewai.agents.agent_builder.base_agent_executor_mixin import (
CrewAgentExecutorMixin,
)
from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
from crewai.agents.tools_handler import ToolsHandler
from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
from crewai.utilities import I18N
from crewai.utilities.constants import TRAINING_DATA_FILE
from crewai.utilities.training_handler import CrewTrainingHandler
from crewai.utilities import I18N
class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
@@ -46,7 +35,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
tools_handler: Optional[InstanceOf[ToolsHandler]] = None
max_iterations: Optional[int] = 15
have_forced_answer: bool = False
force_answer_max_iterations: Optional[int] = None
force_answer_max_iterations: Optional[int] = None # type: ignore # Incompatible types in assignment (expression has type "int | None", base class "CrewAgentExecutorMixin" defined the type as "int")
step_callback: Optional[Any] = None
system_template: Optional[str] = None
prompt_template: Optional[str] = None
@@ -253,6 +242,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
else:
if tool_calling.tool_name.casefold().strip() in [
name.casefold().strip() for name in name_to_tool_map
] or tool_calling.tool_name.casefold().replace("_", " ") in [
name.casefold().strip() for name in name_to_tool_map
]:
observation = tool_usage.use(tool_calling, agent_action.log)
else:

View File

@@ -1,6 +1,7 @@
import re
from typing import Any, Union
from json_repair import repair_json
from langchain.agents.output_parsers import ReActSingleInputOutputParser
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
@@ -48,11 +49,15 @@ class CrewAgentParser(ReActSingleInputOutputParser):
raise OutputParserException(
f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
)
action = action_match.group(1).strip()
action_input = action_match.group(2)
tool_input = action_input.strip(" ")
tool_input = tool_input.strip('"')
return AgentAction(action, tool_input, text)
action = action_match.group(1)
clean_action = self._clean_action(action)
action_input = action_match.group(2).strip()
tool_input = action_input.strip(" ").strip('"')
safe_tool_input = self._safe_repair_json(tool_input)
return AgentAction(clean_action, safe_tool_input, text)
elif includes_answer:
return AgentFinish(
@@ -87,3 +92,30 @@ class CrewAgentParser(ReActSingleInputOutputParser):
llm_output=text,
send_to_llm=True,
)
def _clean_action(self, text: str) -> str:
"""Clean action string by removing non-essential formatting characters."""
return re.sub(r"^\s*\*+\s*|\s*\*+\s*$", "", text).strip()
def _safe_repair_json(self, tool_input: str) -> str:
UNABLE_TO_REPAIR_JSON_RESULTS = ['""', "{}"]
# Skip repair if the input starts and ends with square brackets
# Explanation: The JSON parser has issues handling inputs that are enclosed in square brackets ('[]').
# These are typically valid JSON arrays or strings that do not require repair. Attempting to repair such inputs
# might lead to unintended alterations, such as wrapping the entire input in additional layers or modifying
# the structure in a way that changes its meaning. By skipping the repair for inputs that start and end with
# square brackets, we preserve the integrity of these valid JSON structures and avoid unnecessary modifications.
if tool_input.startswith("[") and tool_input.endswith("]"):
return tool_input
# Before repair, handle common LLM issues:
# 1. Replace """ with " to avoid JSON parser errors
tool_input = tool_input.replace('"""', '"')
result = repair_json(tool_input)
if result in UNABLE_TO_REPAIR_JSON_RESULTS:
return tool_input
return str(result)

View File

@@ -1,8 +1,15 @@
import click
import pkg_resources
from crewai.memory.storage.kickoff_task_outputs_storage import (
KickoffTaskOutputsSQLiteStorage,
)
from .create_crew import create_crew
from .train_crew import train_crew
from .replay_from_task import replay_task_command
from .reset_memories_command import reset_memories_command
@click.group()
@@ -48,5 +55,76 @@ def train(n_iterations: int):
train_crew(n_iterations)
@crewai.command()
@click.option(
"-t",
"--task_id",
type=str,
help="Replay the crew from this task ID, including all subsequent tasks.",
)
def replay(task_id: str) -> None:
"""
Replay the crew execution from a specific task.
Args:
task_id (str): The ID of the task to replay from.
"""
try:
click.echo(f"Replaying the crew from task {task_id}")
replay_task_command(task_id)
except Exception as e:
click.echo(f"An error occurred while replaying: {e}", err=True)
@crewai.command()
def log_tasks_outputs() -> None:
"""
Retrieve your latest crew.kickoff() task outputs.
"""
try:
storage = KickoffTaskOutputsSQLiteStorage()
tasks = storage.load()
if not tasks:
click.echo(
"No task outputs found. Only crew kickoff task outputs are logged."
)
return
for index, task in enumerate(tasks, 1):
click.echo(f"Task {index}: {task['task_id']}")
click.echo(f"Description: {task['expected_output']}")
click.echo("------")
except Exception as e:
click.echo(f"An error occurred while logging task outputs: {e}", err=True)
@crewai.command()
@click.option("-l", "--long", is_flag=True, help="Reset LONG TERM memory")
@click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
@click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
@click.option(
"-k",
"--kickoff-outputs",
is_flag=True,
help="Reset LATEST KICKOFF TASK OUTPUTS",
)
@click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
def reset_memories(long, short, entities, kickoff_outputs, all):
"""
Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
"""
try:
if not all and not (long or short or entities or kickoff_outputs):
click.echo(
"Please specify at least one memory type to reset using the appropriate flags."
)
return
reset_memories_command(long, short, entities, kickoff_outputs, all)
except Exception as e:
click.echo(f"An error occurred while resetting memories: {e}", err=True)
if __name__ == "__main__":
crewai()

View File

@@ -0,0 +1,24 @@
import subprocess
import click
def replay_task_command(task_id: str) -> None:
"""
Replay the crew execution from a specific task.
Args:
task_id (str): The ID of the task to replay from.
"""
command = ["poetry", "run", "replay", task_id]
try:
result = subprocess.run(command, capture_output=False, text=True, check=True)
if result.stderr:
click.echo(result.stderr, err=True)
except subprocess.CalledProcessError as e:
click.echo(f"An error occurred while replaying the task: {e}", err=True)
click.echo(e.output, err=True)
except Exception as e:
click.echo(f"An unexpected error occurred: {e}", err=True)

View File

@@ -0,0 +1,45 @@
import subprocess
import click
from crewai.memory.entity.entity_memory import EntityMemory
from crewai.memory.long_term.long_term_memory import LongTermMemory
from crewai.memory.short_term.short_term_memory import ShortTermMemory
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
"""
Replay the crew execution from a specific task.
Args:
task_id (str): The ID of the task to replay from.
"""
try:
if all:
ShortTermMemory().reset()
EntityMemory().reset()
LongTermMemory().reset()
TaskOutputStorageHandler().reset()
click.echo("All memories have been reset.")
else:
if long:
LongTermMemory().reset()
click.echo("Long term memory has been reset.")
if short:
ShortTermMemory().reset()
click.echo("Short term memory has been reset.")
if entity:
EntityMemory().reset()
click.echo("Entity memory has been reset.")
if kickoff_outputs:
TaskOutputStorageHandler().reset()
click.echo("Latest Kickoff outputs stored has been reset.")
except subprocess.CalledProcessError as e:
click.echo(f"An error occurred while resetting the memories: {e}", err=True)
click.echo(e.output, err=True)
except Exception as e:
click.echo(f"An unexpected error occurred: {e}", err=True)

View File

@@ -12,4 +12,4 @@ reporting_task:
Make sure the report is detailed and contains any and all relevant information.
expected_output: >
A fully fledge reports with the mains topics, each with a full section of information.
Formated as markdown with out '```'
Formatted as markdown without '```'

View File

@@ -2,9 +2,15 @@
import sys
from {{folder_name}}.crew import {{crew_name}}Crew
# This main file is intended to be a way for your to run your
# crew locally, so refrain from adding necessary logic into this file.
# Replace with inputs you want to test with, it will automatically
# interpolate any tasks and agents information
def run():
# Replace with your inputs, it will automatically interpolate any tasks and agents information
"""
Run the crew.
"""
inputs = {
'topic': 'AI LLMs'
}
@@ -15,9 +21,21 @@ def train():
"""
Train the crew for a given number of iterations.
"""
inputs = {"topic": "AI LLMs"}
inputs = {
"topic": "AI LLMs"
}
try:
{{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]), inputs=inputs)
except Exception as e:
raise Exception(f"An error occurred while training the crew: {e}")
def replay():
"""
Replay the crew execution from a specific task.
"""
try:
{{crew_name}}Crew().crew().replay(task_id=sys.argv[1])
except Exception as e:
raise Exception(f"An error occurred while replaying the crew: {e}")

View File

@@ -6,11 +6,12 @@ authors = ["Your Name <you@example.com>"]
[tool.poetry.dependencies]
python = ">=3.10,<=3.13"
crewai = { extras = ["tools"], version = "^0.35.8" }
crewai = { extras = ["tools"], version = "^0.41.0" }
[tool.poetry.scripts]
{{folder_name}} = "{{folder_name}}.main:run"
train = "{{folder_name}}.main:train"
replay = "{{folder_name}}.main:replay"
[build-system]
requires = ["poetry-core"]

View File

@@ -1,6 +1,8 @@
import asyncio
import json
import uuid
from concurrent.futures import Future
from hashlib import md5
from typing import Any, Dict, List, Optional, Tuple, Union
from langchain_core.callbacks import BaseCallbackHandler
@@ -20,16 +22,28 @@ from pydantic_core import PydanticCustomError
from crewai.agent import Agent
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.agents.cache import CacheHandler
from crewai.crews.crew_output import CrewOutput
from crewai.memory.entity.entity_memory import EntityMemory
from crewai.memory.long_term.long_term_memory import LongTermMemory
from crewai.memory.short_term.short_term_memory import ShortTermMemory
from crewai.process import Process
from crewai.task import Task
from crewai.tasks.conditional_task import ConditionalTask
from crewai.tasks.task_output import TaskOutput
from crewai.telemetry import Telemetry
from crewai.tools.agent_tools import AgentTools
from crewai.utilities import I18N, FileHandler, Logger, RPMController
from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
from crewai.utilities.constants import (
TRAINED_AGENTS_DATA_FILE,
TRAINING_DATA_FILE,
)
from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
from crewai.utilities.formatter import (
aggregate_raw_outputs_from_task_outputs,
aggregate_raw_outputs_from_tasks,
)
from crewai.utilities.planning_handler import CrewPlanner
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
from crewai.utilities.training_handler import CrewTrainingHandler
try:
@@ -57,10 +71,10 @@ class Crew(BaseModel):
max_rpm: Maximum number of requests per minute for the crew execution to be respected.
prompt_file: Path to the prompt json file to be used for the crew.
id: A unique identifier for the crew instance.
full_output: Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.
task_callback: Callback to be executed after each task for every agents execution.
step_callback: Callback to be executed after each step for every agents execution.
share_crew: Whether you want to share the complete crew information and execution with crewAI to make the library better, and allow us to train models.
planning: Plan the crew execution and add the plan to the crew.
"""
__hash__ = object.__hash__ # type: ignore
@@ -74,6 +88,13 @@ class Crew(BaseModel):
_entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
_train: Optional[bool] = PrivateAttr(default=False)
_train_iteration: Optional[int] = PrivateAttr()
_inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
_logging_color: str = PrivateAttr(
default="bold_purple",
)
_task_output_handler: TaskOutputStorageHandler = PrivateAttr(
default_factory=TaskOutputStorageHandler
)
cache: bool = Field(default=True)
model_config = ConfigDict(arbitrary_types_allowed=True)
@@ -93,10 +114,6 @@ class Crew(BaseModel):
default=None,
description="Metrics for the LLM usage during all tasks execution.",
)
full_output: Optional[bool] = Field(
default=False,
description="Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.",
)
manager_llm: Optional[Any] = Field(
description="Language model that will run the agent.", default=None
)
@@ -133,6 +150,18 @@ class Crew(BaseModel):
default=False,
description="output_log_file",
)
planning: Optional[bool] = Field(
default=False,
description="Plan the crew execution and add the plan to the crew.",
)
task_execution_output_json_files: Optional[List[str]] = Field(
default=None,
description="List of file paths for task execution JSON files.",
)
execution_logs: List[Dict[str, Any]] = Field(
default=[],
description="List of execution logs for tasks",
)
@field_validator("id", mode="before")
@classmethod
@@ -168,7 +197,6 @@ class Crew(BaseModel):
self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
self._telemetry = Telemetry()
self._telemetry.set_tracer()
self._telemetry.crew_creation(self)
return self
@model_validator(mode="after")
@@ -232,7 +260,7 @@ class Crew(BaseModel):
if task.agent is None:
raise PydanticCustomError(
"missing_agent_in_task",
f"Sequential process error: Agent is missing in the task with the following description: {task.description}", # type: ignore Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
f"Sequential process error: Agent is missing in the task with the following description: {task.description}", # type: ignore # Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
{},
)
@@ -252,6 +280,93 @@ class Crew(BaseModel):
return self
@model_validator(mode="after")
def validate_end_with_at_most_one_async_task(self):
"""Validates that the crew ends with at most one asynchronous task."""
final_async_task_count = 0
# Traverse tasks backward
for task in reversed(self.tasks):
if task.async_execution:
final_async_task_count += 1
else:
break # Stop traversing as soon as a non-async task is encountered
if final_async_task_count > 1:
raise PydanticCustomError(
"async_task_count",
"The crew must end with at most one asynchronous task.",
{},
)
return self
@model_validator(mode="after")
def validate_first_task(self) -> "Crew":
"""Ensure the first task is not a ConditionalTask."""
if self.tasks and isinstance(self.tasks[0], ConditionalTask):
raise PydanticCustomError(
"invalid_first_task",
"The first task cannot be a ConditionalTask.",
{},
)
return self
@model_validator(mode="after")
def validate_async_tasks_not_async(self) -> "Crew":
"""Ensure that ConditionalTask is not async."""
for task in self.tasks:
if task.async_execution and isinstance(task, ConditionalTask):
raise PydanticCustomError(
"invalid_async_conditional_task",
f"Conditional Task: {task.description} , cannot be executed asynchronously.", # type: ignore # Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
{},
)
return self
@model_validator(mode="after")
def validate_async_task_cannot_include_sequential_async_tasks_in_context(self):
"""
Validates that if a task is set to be executed asynchronously,
it cannot include other asynchronous tasks in its context unless
separated by a synchronous task.
"""
for i, task in enumerate(self.tasks):
if task.async_execution and task.context:
for context_task in task.context:
if context_task.async_execution:
for j in range(i - 1, -1, -1):
if self.tasks[j] == context_task:
raise ValueError(
f"Task '{task.description}' is asynchronous and cannot include other sequential asynchronous tasks in its context."
)
if not self.tasks[j].async_execution:
break
return self
@model_validator(mode="after")
def validate_context_no_future_tasks(self):
"""Validates that a task's context does not include future tasks."""
task_indices = {id(task): i for i, task in enumerate(self.tasks)}
for task in self.tasks:
if task.context:
for context_task in task.context:
if id(context_task) not in task_indices:
continue # Skip context tasks not in the main tasks list
if task_indices[id(context_task)] > task_indices[id(task)]:
raise ValueError(
f"Task '{task.description}' has a context dependency on a future task '{context_task.description}', which is not allowed."
)
return self
@property
def key(self) -> str:
source = [agent.key for agent in self.agents] + [
task.key for task in self.tasks
]
return md5("|".join(source).encode()).hexdigest()
def _setup_from_config(self):
assert self.config is not None, "Config should not be None."
@@ -314,40 +429,45 @@ class Crew(BaseModel):
def kickoff(
self,
inputs: Optional[Dict[str, Any]] = {},
) -> Union[str, Dict[str, Any]]:
inputs: Optional[Dict[str, Any]] = None,
) -> CrewOutput:
"""Starts the crew to work on its assigned tasks."""
self._execution_span = self._telemetry.crew_execution_span(self, inputs)
# type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
self._interpolate_inputs(inputs)
self._task_output_handler.reset()
self._logging_color = "bold_purple"
if inputs is not None:
self._inputs = inputs
self._interpolate_inputs(inputs)
self._set_tasks_callbacks()
i18n = I18N(prompt_file=self.prompt_file)
for agent in self.agents:
# type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
agent.i18n = i18n
# type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
agent.crew = self # type: ignore[attr-defined]
# TODO: Create an AgentFunctionCalling protocol for future refactoring
if not agent.function_calling_llm:
agent.function_calling_llm = self.function_calling_llm
if not agent.function_calling_llm: # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
agent.function_calling_llm = self.function_calling_llm # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
if agent.allow_code_execution:
agent.tools += agent.get_code_execution_tools()
if agent.allow_code_execution: # type: ignore # BaseAgent" has no attribute "allow_code_execution"
agent.tools += agent.get_code_execution_tools() # type: ignore # "BaseAgent" has no attribute "get_code_execution_tools"; maybe "get_delegation_tools"?
if not agent.step_callback:
agent.step_callback = self.step_callback
if not agent.step_callback: # type: ignore # "BaseAgent" has no attribute "step_callback"
agent.step_callback = self.step_callback # type: ignore # "BaseAgent" has no attribute "step_callback"
agent.create_agent_executor()
if self.planning:
self._handle_crew_planning()
metrics = []
if self.process == Process.sequential:
result = self._run_sequential_process()
elif self.process == Process.hierarchical:
result, manager_metrics = self._run_hierarchical_process()
metrics.append(manager_metrics)
result = self._run_hierarchical_process()
else:
raise NotImplementedError(
f"The process '{self.process}' is not implemented yet."
@@ -360,11 +480,9 @@ class Crew(BaseModel):
return result
def kickoff_for_each(
self, inputs: List[Dict[str, Any]]
) -> List[Union[str, Dict[str, Any]]]:
def kickoff_for_each(self, inputs: List[Dict[str, Any]]) -> List[CrewOutput]:
"""Executes the Crew's workflow for each input in the list and aggregates results."""
results = []
results: List[CrewOutput] = []
# Initialize the parent crew's usage metrics
total_usage_metrics = {
@@ -386,15 +504,14 @@ class Crew(BaseModel):
results.append(output)
self.usage_metrics = total_usage_metrics
self._task_output_handler.reset()
return results
async def kickoff_async(
self, inputs: Optional[Dict[str, Any]] = {}
) -> Union[str, Dict]:
async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = {}) -> CrewOutput:
"""Asynchronous kickoff method to start the crew execution."""
return await asyncio.to_thread(self.kickoff, inputs)
async def kickoff_for_each_async(self, inputs: List[Dict]) -> List[Any]:
async def kickoff_for_each_async(self, inputs: List[Dict]) -> List[CrewOutput]:
crew_copies = [self.copy() for _ in inputs]
async def run_crew(crew, input_data):
@@ -404,6 +521,10 @@ class Crew(BaseModel):
asyncio.create_task(run_crew(crew_copies[i], inputs[i]))
for i in range(len(inputs))
]
tasks = [
asyncio.create_task(run_crew(crew_copies[i], inputs[i]))
for i in range(len(inputs))
]
results = await asyncio.gather(*tasks)
@@ -420,53 +541,68 @@ class Crew(BaseModel):
self.usage_metrics = total_usage_metrics
total_usage_metrics = {
"total_tokens": 0,
"prompt_tokens": 0,
"completion_tokens": 0,
"successful_requests": 0,
}
for crew in crew_copies:
if crew.usage_metrics:
for key in total_usage_metrics:
total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
self.usage_metrics = total_usage_metrics
self._task_output_handler.reset()
return results
def _run_sequential_process(self) -> str:
"""Executes tasks sequentially and returns the final output."""
task_output = ""
def _handle_crew_planning(self):
"""Handles the Crew planning."""
self._logger.log("info", "Planning the crew execution")
result = CrewPlanner(self.tasks)._handle_crew_planning()
for task in self.tasks:
if task.agent.allow_delegation: # type: ignore # Item "None" of "Agent | None" has no attribute "allow_delegation"
agents_for_delegation = [
agent for agent in self.agents if agent != task.agent
]
if len(self.agents) > 1 and len(agents_for_delegation) > 0:
task.tools += task.agent.get_delegation_tools(agents_for_delegation)
for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
task.description += step_plan
role = task.agent.role if task.agent is not None else "None"
self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
self._logger.log(
"info", f"== Starting Task: {task.description}", color="bold_purple"
)
if self.output_log_file:
self._file_handler.log(
agent=role, task=task.description, status="started"
)
output = task.execute(context=task_output)
if not task.async_execution:
task_output = output
role = task.agent.role if task.agent is not None else "None"
self._logger.log("debug", f"== [{role}] Task output: {task_output}\n\n")
if self.output_log_file:
self._file_handler.log(agent=role, task=task_output, status="completed")
self._finish_execution(task_output)
token_usage = self.calculate_usage_metrics()
# type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
return self._format_output(task_output, token_usage)
def _run_hierarchical_process(
def _store_execution_log(
self,
) -> Tuple[Union[str, Dict[str, Any]], Dict[str, Any]]:
"""Creates and assigns a manager agent to make sure the crew completes the tasks."""
task: Task,
output: TaskOutput,
task_index: int,
was_replayed: bool = False,
):
if self._inputs:
inputs = self._inputs
else:
inputs = {}
log = {
"task": task,
"output": {
"description": output.description,
"summary": output.summary,
"raw": output.raw,
"pydantic": output.pydantic,
"json_dict": output.json_dict,
"output_format": output.output_format,
"agent": output.agent,
},
"task_index": task_index,
"inputs": inputs,
"was_replayed": was_replayed,
}
self._task_output_handler.update(task_index, log)
def _run_sequential_process(self) -> CrewOutput:
"""Executes tasks sequentially and returns the final output."""
return self._execute_tasks(self.tasks)
def _run_hierarchical_process(self) -> CrewOutput:
"""Creates and assigns a manager agent to make sure the crew completes the tasks."""
self._create_manager_agent()
return self._execute_tasks(self.tasks, self.manager_agent)
def _create_manager_agent(self):
i18n = I18N(prompt_file=self.prompt_file)
if self.manager_agent is not None:
self.manager_agent.allow_delegation = True
@@ -485,37 +621,263 @@ class Crew(BaseModel):
)
self.manager_agent = manager
task_output = ""
def _execute_tasks(
self,
tasks: List[Task],
manager: Optional[BaseAgent] = None,
start_index: Optional[int] = 0,
was_replayed: bool = False,
) -> CrewOutput:
"""Executes tasks sequentially and returns the final output.
for task in self.tasks:
self._logger.log("debug", f"Working Agent: {manager.role}")
self._logger.log("info", f"Starting Task: {task.description}")
Args:
tasks (List[Task]): List of tasks to execute
manager (Optional[BaseAgent], optional): Manager agent to use for delegation. Defaults to None.
if self.output_log_file:
self._file_handler.log(
agent=manager.role, task=task.description, status="started"
Returns:
CrewOutput: Final output of the crew
"""
task_outputs: List[TaskOutput] = []
futures: List[Tuple[Task, Future[TaskOutput], int]] = []
last_sync_output: Optional[TaskOutput] = None
for task_index, task in enumerate(tasks):
if start_index is not None and task_index < start_index:
if task.output:
if task.async_execution:
task_outputs.append(task.output)
else:
task_outputs = [task.output]
last_sync_output = task.output
continue
agent_to_use = self._get_agent_to_use(task, manager)
if agent_to_use is None:
raise ValueError(
f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
)
if task.agent:
manager.tools = task.agent.get_delegation_tools([task.agent])
self._prepare_agent_tools(task, manager)
self._log_task_start(task, agent_to_use.role)
if isinstance(task, ConditionalTask):
skipped_task_output = self._handle_conditional_task(
task, task_outputs, futures, task_index, was_replayed
)
if skipped_task_output:
continue
if task.async_execution:
context = self._get_context(
task, [last_sync_output] if last_sync_output else []
)
future = task.execute_async(
agent=agent_to_use,
context=context,
tools=agent_to_use.tools,
)
futures.append((task, future, task_index))
else:
manager.tools = manager.get_delegation_tools(self.agents)
task_output = task.execute(
agent=manager, context=task_output, tools=manager.tools
)
if futures:
task_outputs = self._process_async_tasks(futures, was_replayed)
futures.clear()
self._logger.log("debug", f"[{manager.role}] Task output: {task_output}")
if self.output_log_file:
self._file_handler.log(
agent=manager.role, task=task_output, status="completed"
context = self._get_context(task, task_outputs)
task_output = task.execute_sync(
agent=agent_to_use,
context=context,
tools=agent_to_use.tools,
)
task_outputs = [task_output]
self._process_task_result(task, task_output)
self._store_execution_log(task, task_output, task_index, was_replayed)
self._finish_execution(task_output)
if futures:
task_outputs = self._process_async_tasks(futures, was_replayed)
# type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
return self._create_crew_output(task_outputs)
def _handle_conditional_task(
self,
task: ConditionalTask,
task_outputs: List[TaskOutput],
futures: List[Tuple[Task, Future[TaskOutput], int]],
task_index: int,
was_replayed: bool,
) -> Optional[TaskOutput]:
if futures:
task_outputs = self._process_async_tasks(futures, was_replayed)
futures.clear()
previous_output = task_outputs[task_index - 1] if task_outputs else None
if previous_output is not None and not task.should_execute(previous_output):
self._logger.log(
"debug",
f"Skipping conditional task: {task.description}",
color="yellow",
)
skipped_task_output = task.get_skipped_task_output()
if not was_replayed:
self._store_execution_log(task, skipped_task_output, task_index)
return skipped_task_output
return None
def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
if self.process == Process.hierarchical:
if manager:
self._update_manager_tools(task, manager)
else:
raise ValueError("Manager agent is required for hierarchical process.")
elif task.agent and task.agent.allow_delegation:
self._add_delegation_tools(task)
def _get_agent_to_use(
self, task: Task, manager: Optional[BaseAgent]
) -> Optional[BaseAgent]:
if self.process == Process.hierarchical:
return manager
return task.agent
def _add_delegation_tools(self, task: Task):
agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
delegation_tools = task.agent.get_delegation_tools(agents_for_delegation)
# Add tools if they are not already in task.tools
for new_tool in delegation_tools:
# Find the index of the tool with the same name
existing_tool_index = next(
(
index
for index, tool in enumerate(task.tools or [])
if tool.name == new_tool.name
),
None,
)
if not task.tools:
task.tools = []
if existing_tool_index is not None:
# Replace the existing tool
task.tools[existing_tool_index] = new_tool
else:
# Add the new tool
task.tools.append(new_tool)
def _log_task_start(self, task: Task, role: str = "None"):
color = self._logging_color
self._logger.log("debug", f"== Working Agent: {role}", color=color)
self._logger.log("info", f"== Starting Task: {task.description}", color=color)
if self.output_log_file:
self._file_handler.log(agent=role, task=task.description, status="started")
def _update_manager_tools(self, task: Task, manager: BaseAgent):
if task.agent:
manager.tools = task.agent.get_delegation_tools([task.agent])
else:
manager.tools = manager.get_delegation_tools(self.agents)
def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
context = (
aggregate_raw_outputs_from_tasks(task.context)
if task.context
else aggregate_raw_outputs_from_task_outputs(task_outputs)
)
return context
def _process_task_result(self, task: Task, output: TaskOutput) -> None:
role = task.agent.role if task.agent is not None else "None"
self._logger.log("debug", f"== [{role}] Task output: {output}\n\n")
if self.output_log_file:
self._file_handler.log(agent=role, task=output, status="completed")
def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
if len(task_outputs) != 1:
raise ValueError(
"Something went wrong. Kickoff should return only one task output."
)
final_task_output = task_outputs[0]
final_string_output = final_task_output.raw
self._finish_execution(final_string_output)
token_usage = self.calculate_usage_metrics()
return self._format_output(task_output, token_usage), token_usage
return CrewOutput(
raw=final_task_output.raw,
pydantic=final_task_output.pydantic,
json_dict=final_task_output.json_dict,
tasks_output=[task.output for task in self.tasks if task.output],
token_usage=token_usage,
)
def _process_async_tasks(
self,
futures: List[Tuple[Task, Future[TaskOutput], int]],
was_replayed: bool = False,
) -> List[TaskOutput]:
task_outputs: List[TaskOutput] = []
for future_task, future, task_index in futures:
task_output = future.result()
task_outputs.append(task_output)
self._process_task_result(future_task, task_output)
self._store_execution_log(
future_task, task_output, task_index, was_replayed
)
return task_outputs
def _find_task_index(
self, task_id: str, stored_outputs: List[Any]
) -> Optional[int]:
return next(
(
index
for (index, d) in enumerate(stored_outputs)
if d["task_id"] == str(task_id)
),
None,
)
def replay(
self, task_id: str, inputs: Optional[Dict[str, Any]] = None
) -> CrewOutput:
stored_outputs = self._task_output_handler.load()
if not stored_outputs:
raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
start_index = self._find_task_index(task_id, stored_outputs)
if start_index is None:
raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
replay_inputs = (
inputs if inputs is not None else stored_outputs[start_index]["inputs"]
)
self._inputs = replay_inputs
if replay_inputs:
self._interpolate_inputs(replay_inputs)
if self.process == Process.hierarchical:
self._create_manager_agent()
for i in range(start_index):
stored_output = stored_outputs[i][
"output"
] # for adding context to the task
task_output = TaskOutput(
description=stored_output["description"],
agent=stored_output["agent"],
raw=stored_output["raw"],
pydantic=stored_output["pydantic"],
json_dict=stored_output["json_dict"],
output_format=stored_output["output_format"],
)
self.tasks[i].output = task_output
self._logging_color = "bold_blue"
result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
return result
def copy(self):
"""Create a deep copy of the Crew."""
@@ -567,31 +929,15 @@ class Crew(BaseModel):
for agent in self.agents:
agent.interpolate_inputs(inputs)
def _format_output(
self, output: str, token_usage: Optional[Dict[str, Any]] = None
) -> Union[str, Dict[str, Any]]:
"""
Formats the output of the crew execution.
If full_output is True, then returned data type will be a dictionary else returned outputs are string
"""
if self.full_output:
return { # type: ignore # Incompatible return value type (got "dict[str, Sequence[str | TaskOutput | None]]", expected "str")
"final_output": output,
"tasks_outputs": [task.output for task in self.tasks if task],
"usage_metrics": token_usage,
}
else:
return output
def _finish_execution(self, output) -> None:
def _finish_execution(self, final_string_output: str) -> None:
if self.max_rpm:
self._rpm_controller.stop_rpm_counter()
if agentops:
agentops.end_session(
end_state="Success", end_state_reason="Finished Execution"
end_state="Success",
end_state_reason="Finished Execution",
)
self._telemetry.end_crew(self, output)
self._telemetry.end_crew(self, final_string_output)
def calculate_usage_metrics(self) -> Dict[str, int]:
"""Calculates and returns the usage metrics."""

View File

@@ -0,0 +1 @@
from .crew_output import CrewOutput

View File

@@ -0,0 +1,50 @@
import json
from typing import Any, Dict, Optional
from pydantic import BaseModel, Field
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
class CrewOutput(BaseModel):
"""Class that represents the result of a crew."""
raw: str = Field(description="Raw output of crew", default="")
pydantic: Optional[BaseModel] = Field(
description="Pydantic output of Crew", default=None
)
json_dict: Optional[Dict[str, Any]] = Field(
description="JSON dict output of Crew", default=None
)
tasks_output: list[TaskOutput] = Field(
description="Output of each task", default=[]
)
token_usage: Dict[str, Any] = Field(
description="Processed token summary", default={}
)
@property
def json(self) -> Optional[str]:
if self.tasks_output[-1].output_format != OutputFormat.JSON:
raise ValueError(
"No JSON output found in the final task. Please make sure to set the output_json property in the final task in your crew."
)
return json.dumps(self.json_dict)
def to_dict(self) -> Dict[str, Any]:
"""Convert json_output and pydantic_output to a dictionary."""
output_dict = {}
if self.json_dict:
output_dict.update(self.json_dict)
elif self.pydantic:
output_dict.update(self.pydantic.model_dump())
return output_dict
def __str__(self):
if self.pydantic:
return str(self.pydantic)
if self.json_dict:
return str(self.json_dict)
return self.raw

View File

@@ -23,3 +23,9 @@ class EntityMemory(Memory):
"""Saves an entity item into the SQLite storage."""
data = f"{item.name}({item.type}): {item.description}"
super().save(data, item.metadata)
def reset(self) -> None:
try:
self.storage.reset()
except Exception as e:
raise Exception(f"An error occurred while resetting the entity memory: {e}")

View File

@@ -30,3 +30,6 @@ class LongTermMemory(Memory):
def search(self, task: str, latest_n: int = 3) -> Dict[str, Any]:
return self.storage.load(task, latest_n) # type: ignore # BUG?: "Storage" has no attribute "load"
def reset(self) -> None:
self.storage.reset()

View File

@@ -18,8 +18,16 @@ class ShortTermMemory(Memory):
)
super().__init__(storage)
def save(self, item: ShortTermMemoryItem) -> None: # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
def save(self, item: ShortTermMemoryItem) -> None:
super().save(item.data, item.metadata, item.agent)
def search(self, query: str, score_threshold: float = 0.35):
return self.storage.search(query=query, score_threshold=score_threshold) # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
def reset(self) -> None:
try:
self.storage.reset()
except Exception as e:
raise Exception(
f"An error occurred while resetting the short-term memory: {e}"
)

View File

@@ -9,3 +9,6 @@ class Storage:
def search(self, key: str) -> Dict[str, Any]: # type: ignore
pass
def reset(self) -> None:
pass

View File

@@ -0,0 +1,166 @@
import json
import sqlite3
from typing import Any, Dict, List, Optional
from crewai.task import Task
from crewai.utilities import Printer
from crewai.utilities.crew_json_encoder import CrewJSONEncoder
from crewai.utilities.paths import db_storage_path
class KickoffTaskOutputsSQLiteStorage:
"""
An updated SQLite storage class for kickoff task outputs storage.
"""
def __init__(
self, db_path: str = f"{db_storage_path()}/latest_kickoff_task_outputs.db"
) -> None:
self.db_path = db_path
self._printer: Printer = Printer()
self._initialize_db()
def _initialize_db(self):
"""
Initializes the SQLite database and creates LTM table
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute(
"""
CREATE TABLE IF NOT EXISTS latest_kickoff_task_outputs (
task_id TEXT PRIMARY KEY,
expected_output TEXT,
output JSON,
task_index INTEGER,
inputs JSON,
was_replayed BOOLEAN,
timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
)
"""
)
conn.commit()
except sqlite3.Error as e:
self._printer.print(
content=f"SAVING KICKOFF TASK OUTPUTS ERROR: An error occurred during database initialization: {e}",
color="red",
)
def add(
self,
task: Task,
output: Dict[str, Any],
task_index: int,
was_replayed: bool = False,
inputs: Dict[str, Any] = {},
):
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute(
"""
INSERT OR REPLACE INTO latest_kickoff_task_outputs
(task_id, expected_output, output, task_index, inputs, was_replayed)
VALUES (?, ?, ?, ?, ?, ?)
""",
(
str(task.id),
task.expected_output,
json.dumps(output, cls=CrewJSONEncoder),
task_index,
json.dumps(inputs),
was_replayed,
),
)
conn.commit()
except sqlite3.Error as e:
self._printer.print(
content=f"SAVING KICKOFF TASK OUTPUTS ERROR: An error occurred during database initialization: {e}",
color="red",
)
def update(
self,
task_index: int,
**kwargs,
):
"""
Updates an existing row in the latest_kickoff_task_outputs table based on task_index.
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
fields = []
values = []
for key, value in kwargs.items():
fields.append(f"{key} = ?")
values.append(
json.dumps(value, cls=CrewJSONEncoder)
if isinstance(value, dict)
else value
)
query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"
values.append(task_index)
cursor.execute(query, tuple(values))
conn.commit()
if cursor.rowcount == 0:
self._printer.print(
f"No row found with task_index {task_index}. No update performed.",
color="red",
)
except sqlite3.Error as e:
self._printer.print(f"UPDATE KICKOFF TASK OUTPUTS ERROR: {e}", color="red")
def load(self) -> Optional[List[Dict[str, Any]]]:
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("""
SELECT *
FROM latest_kickoff_task_outputs
ORDER BY task_index
""")
rows = cursor.fetchall()
results = []
for row in rows:
result = {
"task_id": row[0],
"expected_output": row[1],
"output": json.loads(row[2]),
"task_index": row[3],
"inputs": json.loads(row[4]),
"was_replayed": row[5],
"timestamp": row[6],
}
results.append(result)
return results
except sqlite3.Error as e:
self._printer.print(
content=f"LOADING KICKOFF TASK OUTPUTS ERROR: An error occurred while querying kickoff task outputs: {e}",
color="red",
)
return None
def delete_all(self):
"""
Deletes all rows from the latest_kickoff_task_outputs table.
"""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("DELETE FROM latest_kickoff_task_outputs")
conn.commit()
except sqlite3.Error as e:
self._printer.print(
content=f"ERROR: Failed to delete all kickoff task outputs: {e}",
color="red",
)

View File

@@ -103,3 +103,20 @@ class LTMSQLiteStorage:
color="red",
)
return None
def reset(
self,
) -> None:
"""Resets the LTM table with error handling."""
try:
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("DELETE FROM long_term_memories")
conn.commit()
except sqlite3.Error as e:
self._printer.print(
content=f"MEMORY ERROR: An error occurred while deleting all rows in LTM: {e}",
color="red",
)
return None

View File

@@ -2,6 +2,7 @@ import contextlib
import io
import logging
import os
import shutil
from typing import Any, Dict, List, Optional
from embedchain import App
@@ -71,13 +72,13 @@ class RAGStorage(Storage):
if embedder_config:
config["embedder"] = embedder_config
self.type = type
self.app = App.from_config(config=config)
self.app.llm = FakeLLM()
if allow_reset:
self.app.reset()
def save(self, value: Any, metadata: Dict[str, Any]) -> None: # type: ignore # BUG?: Should be save(key, value, metadata) Signature of "save" incompatible with supertype "Storage"
def save(self, value: Any, metadata: Dict[str, Any]) -> None:
self._generate_embedding(value, metadata)
def search( # type: ignore # BUG?: Signature of "search" incompatible with supertype "Storage"
@@ -102,3 +103,11 @@ class RAGStorage(Storage):
def _generate_embedding(self, text: str, metadata: Dict[str, Any]) -> Any:
with suppress_logging():
self.app.add(text, data_type="text", metadata=metadata)
def reset(self) -> None:
try:
shutil.rmtree(f"{db_storage_path()}/{self.type}")
except Exception as e:
raise Exception(
f"An error occurred while resetting the {self.type} memory: {e}"
)

View File

@@ -1,9 +1,12 @@
import json
import os
import re
import threading
import uuid
from concurrent.futures import Future
from copy import copy
from typing import Any, Dict, List, Optional, Type, Union
from hashlib import md5
from typing import Any, Dict, List, Optional, Tuple, Type, Union
from langchain_openai import ChatOpenAI
from opentelemetry.trace import Span
@@ -11,9 +14,10 @@ from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
from pydantic_core import PydanticCustomError
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
from crewai.telemetry.telemetry import Telemetry
from crewai.utilities.converter import ConverterError
from crewai.utilities.converter import Converter, ConverterError
from crewai.utilities.i18n import I18N
from crewai.utilities.printer import Printer
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
@@ -97,6 +101,10 @@ class Task(BaseModel):
description="Whether the task should have a human review the final answer of the agent",
default=False,
)
converter_cls: Optional[Type[Converter]] = Field(
description="A converter class used to export structured output",
default=None,
)
_telemetry: Telemetry
_execution_span: Span | None = None
@@ -157,91 +165,102 @@ class Task(BaseModel):
)
return self
def wait_for_completion(self) -> str | BaseModel:
"""Wait for asynchronous task completion and return the output."""
assert self.async_execution, "Task is not set to be executed asynchronously."
def execute_sync(
self,
agent: Optional[BaseAgent] = None,
context: Optional[str] = None,
tools: Optional[List[Any]] = None,
) -> TaskOutput:
"""Execute the task synchronously."""
return self._execute_core(agent, context, tools)
if self._thread:
self._thread.join()
self._thread = None
@property
def key(self) -> str:
description = self._original_description or self.description
expected_output = self._original_expected_output or self.expected_output
source = [description, expected_output]
assert self.output, "Task output is not set."
return md5("|".join(source).encode()).hexdigest()
return self.output.exported_output
def execute( # type: ignore # Missing return statement
def execute_async(
self,
agent: BaseAgent | None = None,
context: Optional[str] = None,
tools: Optional[List[Any]] = None,
) -> str:
"""Execute the task.
) -> Future[TaskOutput]:
"""Execute the task asynchronously."""
future: Future[TaskOutput] = Future()
threading.Thread(
target=self._execute_task_async, args=(agent, context, tools, future)
).start()
return future
Returns:
Output of the task.
"""
self._execution_span = self._telemetry.task_started(self)
def _execute_task_async(
self,
agent: Optional[BaseAgent],
context: Optional[str],
tools: Optional[List[Any]],
future: Future[TaskOutput],
) -> None:
"""Execute the task asynchronously with context handling."""
result = self._execute_core(agent, context, tools)
future.set_result(result)
def _execute_core(
self,
agent: Optional[BaseAgent],
context: Optional[str],
tools: Optional[List[Any]],
) -> TaskOutput:
"""Run the core execution logic of the task."""
agent = agent or self.agent
self.agent = agent
if not agent:
raise Exception(
f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
)
if self.context:
# type: ignore # Incompatible types in assignment (expression has type "list[Never]", variable has type "str | None")
context = []
for task in self.context:
if task.async_execution:
task.wait_for_completion()
if task.output:
# type: ignore # Item "str" of "str | None" has no attribute "append"
context.append(task.output.raw_output)
# type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
context = "\n".join(context)
self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
self.prompt_context = context
tools = tools or self.tools
tools = tools or self.tools or []
if self.async_execution:
self._thread = threading.Thread(
target=self._execute, args=(agent, self, context, tools)
)
self._thread.start()
else:
result = self._execute(
task=self,
agent=agent,
context=context,
tools=tools,
)
return result
def _execute(self, agent: "BaseAgent", task, context, tools):
result = agent.execute_task(
task=task,
task=self,
context=context,
tools=tools,
)
exported_output = self._export_output(result)
# type: ignore # the responses are usually str but need to figure out a more elegant solution here
self.output = TaskOutput(
pydantic_output, json_output = self._export_output(result)
task_output = TaskOutput(
description=self.description,
exported_output=exported_output,
raw_output=result,
raw=result,
pydantic=pydantic_output,
json_dict=json_output,
agent=agent.role,
output_format=self._get_output_format(),
)
self.output = task_output
if self.callback:
self.callback(self.output)
if self._execution_span:
self._telemetry.task_ended(self._execution_span, self)
self._telemetry.task_ended(self._execution_span, self, agent.crew)
self._execution_span = None
return exported_output
if self.output_file:
content = (
json_output
if json_output
else pydantic_output.model_dump_json()
if pydantic_output
else result
)
self._save_file(content)
return task_output
def prompt(self) -> str:
"""Prompt the task.
@@ -276,7 +295,7 @@ class Task(BaseModel):
"""Increment the delegations counter."""
self.delegations += 1
def copy(self, agents: Optional[List["BaseAgent"]] = None) -> "Task":
def copy(self, agents: List["BaseAgent"]) -> "Task":
"""Create a deep copy of the Task."""
exclude = {
"id",
@@ -289,7 +308,7 @@ class Task(BaseModel):
copied_data = {k: v for k, v in copied_data.items() if v is not None}
cloned_context = (
[task.copy() for task in self.context] if self.context else None
[task.copy(agents) for task in self.context] if self.context else None
)
def get_agent_by_role(role: str) -> Union["BaseAgent", None]:
@@ -307,81 +326,128 @@ class Task(BaseModel):
return copied_task
def _export_output(self, result: str) -> Any:
exported_result = result
instructions = "I'm gonna convert this raw text into valid JSON."
def _create_converter(self, *args, **kwargs) -> Converter:
"""Create a converter instance."""
if self.agent and not self.converter_cls:
converter = self.agent.get_output_converter(*args, **kwargs)
elif self.converter_cls:
converter = self.converter_cls(*args, **kwargs)
if not converter:
raise Exception("No output converter found or set.")
return converter
def _export_output(
self, result: str
) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
pydantic_output: Optional[BaseModel] = None
json_output: Optional[Dict[str, Any]] = None
if self.output_pydantic or self.output_json:
model = self.output_pydantic or self.output_json
model_output = self._convert_to_model(result)
pydantic_output = (
model_output if isinstance(model_output, BaseModel) else None
)
if isinstance(model_output, str):
try:
json_output = json.loads(model_output)
except json.JSONDecodeError:
json_output = None
else:
json_output = model_output if isinstance(model_output, dict) else None
# try to convert task_output directly to pydantic/json
return pydantic_output, json_output
def _convert_to_model(self, result: str) -> Union[dict, BaseModel, str]:
model = self.output_pydantic or self.output_json
if model is None:
return result
try:
return self._validate_model(result, model)
except Exception:
return self._handle_partial_json(result, model)
def _validate_model(
self, result: str, model: Type[BaseModel]
) -> Union[dict, BaseModel]:
exported_result = model.model_validate_json(result)
if self.output_json:
return exported_result.model_dump()
return exported_result
def _handle_partial_json(
self, result: str, model: Type[BaseModel]
) -> Union[dict, BaseModel, str]:
match = re.search(r"({.*})", result, re.DOTALL)
if match:
try:
# type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
exported_result = model.model_validate_json(result)
exported_result = model.model_validate_json(match.group(0))
if self.output_json:
# type: ignore # "str" has no attribute "model_dump"
return exported_result.model_dump()
return exported_result
except Exception:
# sometimes the response contains valid JSON in the middle of text
match = re.search(r"({.*})", result, re.DOTALL)
if match:
try:
# type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
exported_result = model.model_validate_json(match.group(0))
if self.output_json:
# type: ignore # "str" has no attribute "model_dump"
return exported_result.model_dump()
return exported_result
except Exception:
pass
pass
# type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
llm = getattr(self.agent, "function_calling_llm", None) or self.agent.llm
if not self._is_gpt(llm):
# type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
model_schema = PydanticSchemaParser(model=model).get_schema()
instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
return self._convert_with_instructions(result, model)
converter = self.agent.get_output_converter(
llm=llm, text=result, model=model, instructions=instructions
def _convert_with_instructions(
self, result: str, model: Type[BaseModel]
) -> Union[dict, BaseModel, str]:
llm = self.agent.function_calling_llm or self.agent.llm # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
instructions = self._get_conversion_instructions(model, llm)
converter = self._create_converter(
llm=llm, text=result, model=model, instructions=instructions
)
exported_result = (
converter.to_pydantic() if self.output_pydantic else converter.to_json()
)
if isinstance(exported_result, ConverterError):
Printer().print(
content=f"{exported_result.message} Using raw output instead.",
color="red",
)
if self.output_pydantic:
exported_result = converter.to_pydantic()
elif self.output_json:
exported_result = converter.to_json()
if isinstance(exported_result, ConverterError):
Printer().print(
content=f"{exported_result.message} Using raw output instead.",
color="red",
)
exported_result = result
if self.output_file:
content = (
# type: ignore # "str" has no attribute "json"
exported_result
if not self.output_pydantic
else exported_result.model_dump_json()
)
self._save_file(content)
return result
return exported_result
def _get_output_format(self) -> OutputFormat:
if self.output_json:
return OutputFormat.JSON
if self.output_pydantic:
return OutputFormat.PYDANTIC
return OutputFormat.RAW
def _get_conversion_instructions(self, model: Type[BaseModel], llm: Any) -> str:
instructions = "I'm gonna convert this raw text into valid JSON."
if not self._is_gpt(llm):
model_schema = PydanticSchemaParser(model=model).get_schema()
instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
return instructions
def _save_output(self, content: str) -> None:
if not self.output_file:
raise Exception("Output file path is not set.")
directory = os.path.dirname(self.output_file)
if directory and not os.path.exists(directory):
os.makedirs(directory)
with open(self.output_file, "w", encoding="utf-8") as file:
file.write(content)
def _is_gpt(self, llm) -> bool:
return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
def _save_file(self, result: Any) -> None:
# type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
directory = os.path.dirname(self.output_file)
directory = os.path.dirname(self.output_file) # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
if directory and not os.path.exists(directory):
os.makedirs(directory)
# type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
with open(self.output_file, "w", encoding="utf-8") as file:
with open(self.output_file, "w", encoding="utf-8") as file: # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
file.write(result)
return None

View File

@@ -0,0 +1,4 @@
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
__all__ = ["OutputFormat", "TaskOutput"]

View File

@@ -0,0 +1,47 @@
from typing import Any, Callable
from pydantic import Field
from crewai.task import Task
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput
class ConditionalTask(Task):
"""
A task that can be conditionally executed based on the output of another task.
Note: This cannot be the only task you have in your crew and cannot be the first since its needs context from the previous task.
"""
condition: Callable[[TaskOutput], bool] = Field(
default=None,
description="Maximum number of retries for an agent to execute a task when an error occurs.",
)
def __init__(
self,
condition: Callable[[Any], bool],
**kwargs,
):
super().__init__(**kwargs)
self.condition = condition
def should_execute(self, context: TaskOutput) -> bool:
"""
Determines whether the conditional task should be executed based on the provided context.
Args:
context (Any): The context or output from the previous task that will be evaluated by the condition.
Returns:
bool: True if the task should be executed, False otherwise.
"""
return self.condition(context)
def get_skipped_task_output(self):
return TaskOutput(
description=self.description,
raw="",
agent=self.agent.role if self.agent else "",
output_format=OutputFormat.RAW,
)

View File

@@ -0,0 +1,9 @@
from enum import Enum
class OutputFormat(str, Enum):
"""Enum that represents the output format of a task."""
JSON = "json"
PYDANTIC = "pydantic"
RAW = "raw"

View File

@@ -1,24 +1,60 @@
from typing import Optional, Union
import json
from typing import Any, Dict, Optional
from pydantic import BaseModel, Field, model_validator
from crewai.tasks.output_format import OutputFormat
class TaskOutput(BaseModel):
"""Class that represents the result of a task."""
description: str = Field(description="Description of the task")
summary: Optional[str] = Field(description="Summary of the task", default=None)
exported_output: Union[str, BaseModel] = Field(
description="Output of the task", default=None
raw: str = Field(description="Raw output of the task", default="")
pydantic: Optional[BaseModel] = Field(
description="Pydantic output of task", default=None
)
json_dict: Optional[Dict[str, Any]] = Field(
description="JSON dictionary of task", default=None
)
agent: str = Field(description="Agent that executed the task")
raw_output: str = Field(description="Result of the task")
output_format: OutputFormat = Field(
description="Output format of the task", default=OutputFormat.RAW
)
@model_validator(mode="after")
def set_summary(self):
"""Set the summary field based on the description."""
excerpt = " ".join(self.description.split(" ")[:10])
self.summary = f"{excerpt}..."
return self
def result(self):
return self.exported_output
@property
def json(self) -> Optional[str]:
if self.output_format != OutputFormat.JSON:
raise ValueError(
"""
Invalid output format requested.
If you would like to access the JSON output,
please make sure to set the output_json property for the task
"""
)
return json.dumps(self.json_dict)
def to_dict(self) -> Dict[str, Any]:
"""Convert json_output and pydantic_output to a dictionary."""
output_dict = {}
if self.json_dict:
output_dict.update(self.json_dict)
elif self.pydantic:
output_dict.update(self.pydantic.model_dump())
return output_dict
def __str__(self) -> str:
if self.pydantic:
return str(self.pydantic)
if self.json_dict:
return str(self.json_dict)
return self.raw

View File

@@ -80,7 +80,7 @@ class Telemetry:
self.ready = False
self.trace_set = False
def crew_creation(self, crew):
def crew_creation(self, crew: Crew, inputs: dict[str, Any] | None):
"""Records the creation of a crew."""
if self.ready:
try:
@@ -92,6 +92,7 @@ class Telemetry:
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "python_version", platform.python_version())
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "crew_process", crew.process)
self._add_attribute(span, "crew_memory", crew.memory)
@@ -103,6 +104,7 @@ class Telemetry:
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"goal": agent.goal,
@@ -114,7 +116,7 @@ class Telemetry:
"llm": json.dumps(self._safe_llm_attributes(agent.llm)),
"delegation_enabled?": agent.allow_delegation,
"tools_names": [
tool.name.casefold() for tool in agent.tools
tool.name.casefold() for tool in agent.tools or []
],
}
for agent in crew.agents
@@ -127,19 +129,21 @@ class Telemetry:
json.dumps(
[
{
"key": task.key,
"id": str(task.id),
"description": task.description,
"expected_output": task.expected_output,
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": task.agent.role if task.agent else "None",
"agent_key": task.agent.key if task.agent else None,
"context": (
[task.description for task in task.context]
if task.context
else None
),
"tools_names": [
tool.name.casefold() for tool in task.tools
tool.name.casefold() for tool in task.tools or []
],
}
for task in crew.tasks
@@ -151,23 +155,53 @@ class Telemetry:
self._add_attribute(span, "platform_system", platform.system())
self._add_attribute(span, "platform_version", platform.version())
self._add_attribute(span, "cpus", os.cpu_count())
if crew.share_crew:
self._add_attribute(
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def task_started(self, task: Task) -> Span | None:
def task_started(self, crew: Crew, task: Task) -> Span | None:
"""Records task started in a crew."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
created_span = tracer.start_span("Task Created")
self._add_attribute(created_span, "crew_key", crew.key)
self._add_attribute(created_span, "crew_id", str(crew.id))
self._add_attribute(created_span, "task_key", task.key)
self._add_attribute(created_span, "task_id", str(task.id))
if crew.share_crew:
self._add_attribute(
created_span, "formatted_description", task.description
)
self._add_attribute(
created_span, "formatted_expected_output", task.expected_output
)
created_span.set_status(Status(StatusCode.OK))
created_span.end()
span = tracer.start_span("Task Execution")
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "task_key", task.key)
self._add_attribute(span, "task_id", str(task.id))
self._add_attribute(span, "formatted_description", task.description)
self._add_attribute(
span, "formatted_expected_output", task.expected_output
)
if crew.share_crew:
self._add_attribute(span, "formatted_description", task.description)
self._add_attribute(
span, "formatted_expected_output", task.expected_output
)
return span
except Exception:
@@ -175,13 +209,16 @@ class Telemetry:
return None
def task_ended(self, span: Span, task: Task):
def task_ended(self, span: Span, task: Task, crew: Crew):
"""Records task execution in a crew."""
if self.ready:
try:
self._add_attribute(
span, "output", task.output.raw_output if task.output else ""
)
if crew.share_crew:
self._add_attribute(
span,
"task_output",
task.output.raw if task.output else "",
)
span.set_status(Status(StatusCode.OK))
span.end()
@@ -256,6 +293,8 @@ class Telemetry:
"""Records the complete execution of a crew.
This is only collected if the user has opted-in to share the crew.
"""
self.crew_creation(crew, inputs)
if (self.ready) and (crew.share_crew):
try:
tracer = trace.get_tracer("crewai.telemetry")
@@ -265,14 +304,18 @@ class Telemetry:
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "inputs", json.dumps(inputs))
self._add_attribute(
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
self._add_attribute(
span,
"crew_agents",
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"goal": agent.goal,
@@ -303,6 +346,7 @@ class Telemetry:
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": task.agent.role if task.agent else "None",
"agent_key": task.agent.key if task.agent else None,
"context": (
[task.description for task in task.context]
if task.context
@@ -320,7 +364,7 @@ class Telemetry:
except Exception:
pass
def end_crew(self, crew, output):
def end_crew(self, crew, final_string_output):
if (self.ready) and (crew.share_crew):
try:
self._add_attribute(
@@ -328,7 +372,9 @@ class Telemetry:
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(crew._execution_span, "crew_output", output)
self._add_attribute(
crew._execution_span, "crew_output", final_string_output
)
self._add_attribute(
crew._execution_span,
"crew_tasks_output",

View File

@@ -7,7 +7,7 @@ class AgentTools(BaseAgentTools):
"""Default tools around agent delegation"""
def tools(self):
coworkers = f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
tools = [
StructuredTool.from_function(
func=self.delegate_work,

View File

@@ -8,7 +8,7 @@ from pydantic.v1 import BaseModel, Field
class ToolCalling(BaseModel):
tool_name: str = Field(..., description="The name of the tool to be called.")
arguments: Optional[Dict[str, Any]] = Field(
..., description="A dictinary of arguments to be passed to the tool."
..., description="A dictionary of arguments to be passed to the tool."
)
@@ -17,5 +17,5 @@ class InstructorToolCalling(PydanticBaseModel):
..., description="The name of the tool to be called."
)
arguments: Optional[Dict[str, Any]] = PydanticField(
..., description="A dictinary of arguments to be passed to the tool."
..., description="A dictionary of arguments to be passed to the tool."
)

View File

@@ -11,11 +11,10 @@ from crewai.telemetry import Telemetry
from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
from crewai.utilities import I18N, Converter, ConverterError, Printer
agentops = None
try:
import agentops
except ImportError:
pass
agentops = None
OPENAI_BIGGER_MODELS = ["gpt-4"]
@@ -120,7 +119,7 @@ class ToolUsage:
attempts=self._run_attempts,
)
result = self._format_result(result=result) # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
return result # type: ignore # Fix the reutrn type of this function
return result # type: ignore # Fix the return type of this function
except Exception:
self.task.increment_tools_errors()
@@ -152,16 +151,12 @@ class ToolUsage:
for k, v in calling.arguments.items()
if k in acceptable_args
}
result = tool._run(**arguments)
result = tool.invoke(input=arguments)
except Exception:
if tool.args_schema:
arguments = calling.arguments
result = tool._run(**arguments)
else:
arguments = calling.arguments.values() # type: ignore # Incompatible types in assignment (expression has type "dict_values[str, Any]", variable has type "dict[str, Any]")
result = tool._run(*arguments)
arguments = calling.arguments
result = tool.invoke(input=arguments)
else:
result = tool._run()
result = tool.invoke(input={})
except Exception as e:
self._run_attempts += 1
if self._run_attempts > self._max_parsing_attempts:
@@ -216,7 +211,7 @@ class ToolUsage:
hasattr(original_tool, "result_as_answer")
and original_tool.result_as_answer # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
):
result_as_answer = original_tool.result_as_answer
result_as_answer = original_tool.result_as_answer # type: ignore # Item "None" of "Any | None" has no attribute "result_as_answer"
data["result_as_answer"] = result_as_answer
self.agent.tools_results.append(data)

View File

@@ -16,7 +16,7 @@
"format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task\nYour final answer must be the great and the most complete as possible, it must be outcome described\n\n",
"task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
"expected_output": "\nThis is the expect criteria for your final answer: {expected_output} \n you MUST return the actual complete content as the final answer, not a summary.",
"human_feedback": "You got human feedback on your work, re-avaluate it and give a new Final Answer when ready.\n {human_feedback}",
"human_feedback": "You got human feedback on your work, re-evaluate it and give a new Final Answer when ready.\n {human_feedback}",
"getting_input": "This is the agent's final answer: {final_answer}\nPlease provide feedback: "
},
"errors": {

View File

@@ -2,10 +2,8 @@ import json
from langchain.schema import HumanMessage, SystemMessage
from langchain_openai import ChatOpenAI
from pydantic import model_validator
from crewai.agents.agent_builder.utilities.base_output_converter_base import (
OutputConverter,
)
from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
class ConverterError(Exception):
@@ -19,15 +17,10 @@ class ConverterError(Exception):
class Converter(OutputConverter):
"""Class that converts text into either pydantic or json."""
@model_validator(mode="after")
def check_llm_provider(self):
if not self._is_gpt(self.llm):
self._is_gpt = False
def to_pydantic(self, current_attempt=1):
"""Convert text to pydantic."""
try:
if self._is_gpt:
if self.is_gpt:
return self._create_instructor().to_pydantic()
else:
return self._create_chain().invoke({})
@@ -41,14 +34,14 @@ class Converter(OutputConverter):
def to_json(self, current_attempt=1):
"""Convert text to json."""
try:
if self._is_gpt:
if self.is_gpt:
return self._create_instructor().to_json()
else:
return json.dumps(self._create_chain().invoke({}).model_dump())
except Exception:
except Exception as e:
if current_attempt < self.max_attempts:
return self.to_json(current_attempt + 1)
return ConverterError("Failed to convert text into JSON.")
return ConverterError(f"Failed to convert text into JSON, error: {e}.")
def _create_instructor(self):
"""Create an instructor."""
@@ -75,5 +68,7 @@ class Converter(OutputConverter):
)
return new_prompt | self.llm | parser
def _is_gpt(self, llm) -> bool: # type: ignore # BUG? Name "_is_gpt" defined on line 20 hides name from outer scope
return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
@property
def is_gpt(self) -> bool:
"""Return if llm provided is of gpt from openai."""
return isinstance(self.llm, ChatOpenAI) and self.llm.openai_api_base is None

View File

@@ -0,0 +1,31 @@
from datetime import datetime
import json
from uuid import UUID
from pydantic import BaseModel
class CrewJSONEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, BaseModel):
return self._handle_pydantic_model(obj)
elif isinstance(obj, UUID):
return str(obj)
elif isinstance(obj, datetime):
return obj.isoformat()
return super().default(obj)
def _handle_pydantic_model(self, obj):
try:
data = obj.model_dump()
# Remove circular references
for key, value in data.items():
if isinstance(value, BaseModel):
data[key] = str(
value
) # Convert nested models to string representation
return data
except RecursionError:
return str(
obj
) # Fall back to string representation if circular reference is detected

View File

@@ -17,6 +17,16 @@ class CrewPydanticOutputParser(PydanticOutputParser):
def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
result[0].text = self._transform_in_valid_json(result[0].text)
# Treating edge case of function calling llm returning the name instead of tool_name
json_object = json.loads(result[0].text)
json_object["tool_name"] = (
json_object["name"]
if "tool_name" not in json_object
else json_object["tool_name"]
)
result[0].text = json.dumps(json_object)
json_object = super().parse_result(result)
try:
return self.pydantic_object.parse_obj(json_object)

View File

@@ -1,5 +1,7 @@
import os
import pickle
from datetime import datetime

View File

@@ -0,0 +1,20 @@
from typing import List
from crewai.task import Task
from crewai.tasks.task_output import TaskOutput
def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> str:
"""Generate string context from the task outputs."""
dividers = "\n\n----------\n\n"
# Join task outputs with dividers
context = dividers.join(output.raw for output in task_outputs)
return context
def aggregate_raw_outputs_from_tasks(tasks: List[Task]) -> str:
"""Generate string context from the tasks."""
task_outputs = [task.output for task in tasks if task.output is not None]
return aggregate_raw_outputs_from_task_outputs(task_outputs)

View File

@@ -0,0 +1,64 @@
from typing import List
from pydantic import BaseModel
from crewai.agent import Agent
from crewai.task import Task
class PlannerTaskPydanticOutput(BaseModel):
list_of_plans_per_task: List[str]
class CrewPlanner:
def __init__(self, tasks: List[Task]):
self.tasks = tasks
def _handle_crew_planning(self):
"""Handles the Crew planning by creating detailed step-by-step plans for each task."""
planning_agent = self._create_planning_agent()
tasks_summary = self._create_tasks_summary()
planner_task = self._create_planner_task(planning_agent, tasks_summary)
return planner_task.execute_sync()
def _create_planning_agent(self) -> Agent:
"""Creates the planning agent for the crew planning."""
return Agent(
role="Task Execution Planner",
goal=(
"Your goal is to create an extremely detailed, step-by-step plan based on the tasks and tools "
"available to each agent so that they can perform the tasks in an exemplary manner"
),
backstory="Planner agent for crew planning",
)
def _create_planner_task(self, planning_agent: Agent, tasks_summary: str) -> Task:
"""Creates the planner task using the given agent and tasks summary."""
return Task(
description=(
f"Based on these tasks summary: {tasks_summary} \n Create the most descriptive plan based on the tasks "
"descriptions, tools available, and agents' goals for them to execute their goals with perfection."
),
expected_output="Step by step plan on how the agents can execute their tasks using the available tools with mastery",
agent=planning_agent,
output_pydantic=PlannerTaskPydanticOutput,
)
def _create_tasks_summary(self) -> str:
"""Creates a summary of all tasks."""
tasks_summary = []
for idx, task in enumerate(self.tasks):
tasks_summary.append(
f"""
Task Number {idx + 1} - {task.description}
"task_description": {task.description}
"task_expected_output": {task.expected_output}
"agent": {task.agent.role if task.agent else "None"}
"agent_goal": {task.agent.goal if task.agent else "None"}
"task_tools": {task.tools}
"agent_tools": {task.agent.tools if task.agent else "None"}
"""
)
return " ".join(tasks_summary)

View File

@@ -8,6 +8,10 @@ class Printer:
self._print_bold_green(content)
elif color == "bold_purple":
self._print_bold_purple(content)
elif color == "bold_blue":
self._print_bold_blue(content)
elif color == "yellow":
self._print_yellow(content)
else:
print(content)
@@ -22,3 +26,9 @@ class Printer:
def _print_red(self, content):
print("\033[91m {}\033[00m".format(content))
def _print_bold_blue(self, content):
print("\033[1m\033[94m {}\033[00m".format(content))
def _print_yellow(self, content):
print("\033[93m {}\033[00m".format(content))

View File

@@ -0,0 +1,61 @@
from pydantic import BaseModel, Field
from datetime import datetime
from typing import Dict, Any, Optional, List
from crewai.memory.storage.kickoff_task_outputs_storage import (
KickoffTaskOutputsSQLiteStorage,
)
from crewai.task import Task
class ExecutionLog(BaseModel):
task_id: str
expected_output: Optional[str] = None
output: Dict[str, Any]
timestamp: datetime = Field(default_factory=datetime.now)
task_index: int
inputs: Dict[str, Any] = Field(default_factory=dict)
was_replayed: bool = False
def __getitem__(self, key: str) -> Any:
return getattr(self, key)
class TaskOutputStorageHandler:
def __init__(self) -> None:
self.storage = KickoffTaskOutputsSQLiteStorage()
def update(self, task_index: int, log: Dict[str, Any]):
saved_outputs = self.load()
if saved_outputs is None:
raise ValueError("Logs cannot be None")
if log.get("was_replayed", False):
replayed = {
"task_id": str(log["task"].id),
"expected_output": log["task"].expected_output,
"output": log["output"],
"was_replayed": log["was_replayed"],
"inputs": log["inputs"],
}
self.storage.update(
task_index,
**replayed,
)
else:
self.storage.add(**log)
def add(
self,
task: Task,
output: Dict[str, Any],
task_index: int,
inputs: Dict[str, Any] = {},
was_replayed: bool = False,
):
self.storage.add(task, output, task_index, was_replayed, inputs)
def reset(self):
self.storage.delete_all()
def load(self) -> Optional[List[Dict[str, Any]]]:
return self.storage.load()

View File

@@ -631,8 +631,9 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
crew = Crew(agents=[agent1, agent2], tasks=tasks)
result = crew.kickoff()
assert "bye" not in result.lower()
assert "hi" in result.lower() or "hello" in result.lower()
print("LOWER RESULT", result.raw)
assert "bye" not in result.raw.lower()
assert "hi" in result.raw.lower() or "hello" in result.raw.lower()
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -644,7 +645,7 @@ def test_agent_step_callback():
with patch.object(StepCallback, "callback") as callback:
@tool
def learn_about_AI(topic) -> float:
def learn_about_AI(topic) -> str:
"""Useful for when you need to learn about AI to write an paragraph about it."""
return "AI is a very broad field."
@@ -678,7 +679,7 @@ def test_agent_function_calling_llm():
with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
@tool
def learn_about_AI(topic) -> float:
def learn_about_AI(topic) -> str:
"""Useful for when you need to learn about AI to write an paragraph about it."""
return "AI is a very broad field."
@@ -750,12 +751,11 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
crew = Crew(agents=[agent1], tasks=tasks)
result = crew.kickoff()
assert result == "Howdy!"
pytest.mark.vcr(filter_headers=["authorization"])
print("RESULT: ", result.raw)
assert result.raw == "Howdy!"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tool_usage_information_is_appended_to_agent():
from crewai_tools import BaseTool
@@ -963,3 +963,54 @@ def test_agent_use_trained_data(crew_training_handler):
crew_training_handler.assert_has_calls(
[mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
)
def test_agent_max_retry_limit():
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
max_retry_limit=1,
)
task = Task(
agent=agent,
description="Say the word: Hi",
expected_output="The word: Hi",
human_input=True,
)
error_message = "Error happening while sending prompt to model."
with patch.object(
CrewAgentExecutor, "invoke", wraps=agent.agent_executor.invoke
) as invoke_mock:
invoke_mock.side_effect = Exception(error_message)
assert agent._times_executed == 0
assert agent.max_retry_limit == 1
with pytest.raises(Exception) as e:
agent.execute_task(
task=task,
)
assert e.value.args[0] == error_message
assert agent._times_executed == 2
invoke_mock.assert_has_calls(
[
mock.call(
{
"input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
"tool_names": "",
"tools": "",
}
),
mock.call(
{
"input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
"tool_names": "",
"tools": "",
}
),
]
)

0
tests/agents/__init__.py Normal file
View File

View File

@@ -0,0 +1,36 @@
import hashlib
from typing import Any, List, Optional
from crewai.agents.agent_builder.base_agent import BaseAgent
from pydantic import BaseModel
class TestAgent(BaseAgent):
def execute_task(
self,
task: Any,
context: Optional[str] = None,
tools: Optional[List[Any]] = None,
) -> str:
return ""
def create_agent_executor(self, tools=None) -> None: ...
def _parse_tools(self, tools: List[Any]) -> List[Any]:
return []
def get_delegation_tools(self, agents: List["BaseAgent"]): ...
def get_output_converter(
self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
): ...
def test_key():
agent = TestAgent(
role="test role",
goal="test goal",
backstory="test backstory",
)
hash = hashlib.md5("test role|test goal|test backstory".encode()).hexdigest()
assert agent.key == hash

View File

@@ -0,0 +1,378 @@
import pytest
from crewai.agents.parser import CrewAgentParser
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
@pytest.fixture
def parser():
p = CrewAgentParser()
p.agent = MockAgent()
return p
def test_valid_action_parsing_special_characters(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: what's the temperature in SF?"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what's the temperature in SF?"
def test_valid_action_parsing_with_json_tool_input(parser):
text = """
Thought: Let's find the information
Action: query
Action Input: ** {"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we've discussed recent advancements in AI applications in healthcare, it's crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}
"""
result = parser.parse(text)
assert isinstance(result, AgentAction)
expected_tool_input = '{"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we\'ve discussed recent advancements in AI applications in healthcare, it\'s crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}'
assert result.tool == "query"
assert result.tool_input == expected_tool_input
def test_valid_action_parsing_with_quotes(parser):
text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "temperature in SF"'
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "temperature in SF"
def test_valid_action_parsing_with_curly_braces(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: {temperature in SF}"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "{temperature in SF}"
def test_valid_action_parsing_with_angle_brackets(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: <temperature in SF>"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "<temperature in SF>"
def test_valid_action_parsing_with_parentheses(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: (temperature in SF)"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "(temperature in SF)"
def test_valid_action_parsing_with_mixed_brackets(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: [temperature in {SF}]"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "[temperature in {SF}]"
def test_valid_action_parsing_with_nested_quotes(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in 'SF'?\""
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what's the temperature in 'SF'?"
def test_valid_action_parsing_with_incomplete_json(parser):
text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"'
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == '{"query": "temperature in SF"}'
def test_valid_action_parsing_with_special_characters(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? @$%^&*"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is the temperature in SF? @$%^&*"
def test_valid_action_parsing_with_combination(parser):
text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "[what is the temperature in SF?]"'
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "[what is the temperature in SF?]"
def test_valid_action_parsing_with_mixed_quotes(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in SF?\""
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what's the temperature in SF?"
def test_valid_action_parsing_with_newlines(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is\nthe temperature in SF?"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is\nthe temperature in SF?"
def test_valid_action_parsing_with_escaped_characters(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? \\n"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is the temperature in SF? \\n"
def test_valid_action_parsing_with_json_string(parser):
text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"}'
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == '{"query": "temperature in SF"}'
def test_valid_action_parsing_with_unbalanced_quotes(parser):
text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what is the temperature in SF?"
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is the temperature in SF?"
def test_clean_action_no_formatting(parser):
action = "Ask question to senior researcher"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_leading_asterisks(parser):
action = "** Ask question to senior researcher"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_trailing_asterisks(parser):
action = "Ask question to senior researcher **"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_leading_and_trailing_asterisks(parser):
action = "** Ask question to senior researcher **"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_multiple_leading_asterisks(parser):
action = "**** Ask question to senior researcher"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_multiple_trailing_asterisks(parser):
action = "Ask question to senior researcher ****"
cleaned_action = parser._clean_action(action)
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_spaces_and_asterisks(parser):
action = " ** Ask question to senior researcher ** "
cleaned_action = parser._clean_action(action)
print(f"Original action: '{action}'")
print(f"Cleaned action: '{cleaned_action}'")
assert cleaned_action == "Ask question to senior researcher"
def test_clean_action_with_only_asterisks(parser):
action = "****"
cleaned_action = parser._clean_action(action)
assert cleaned_action == ""
def test_clean_action_with_empty_string(parser):
action = ""
cleaned_action = parser._clean_action(action)
assert cleaned_action == ""
def test_valid_final_answer_parsing(parser):
text = (
"Thought: I found the information\nFinal Answer: The temperature is 100 degrees"
)
result = parser.parse(text)
assert isinstance(result, AgentFinish)
assert result.return_values["output"] == "The temperature is 100 degrees"
def test_missing_action_error(parser):
text = "Thought: Let's find the temperature\nAction Input: what is the temperature in SF?"
with pytest.raises(OutputParserException) as exc_info:
parser.parse(text)
assert "Could not parse LLM output" in str(exc_info.value)
def test_missing_action_input_error(parser):
text = "Thought: Let's find the temperature\nAction: search"
with pytest.raises(OutputParserException) as exc_info:
parser.parse(text)
assert "Could not parse LLM output" in str(exc_info.value)
def test_action_and_final_answer_error(parser):
text = "Thought: I found the information\nAction: search\nAction Input: what is the temperature in SF?\nFinal Answer: The temperature is 100 degrees"
with pytest.raises(OutputParserException) as exc_info:
parser.parse(text)
assert "both perform Action and give a Final Answer" in str(exc_info.value)
def test_safe_repair_json(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": Senior Researcher'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_unrepairable(parser):
invalid_json = "{invalid_json"
result = parser._safe_repair_json(invalid_json)
print("result:", invalid_json)
assert result == invalid_json # Should return the original if unrepairable
def test_safe_repair_json_missing_quotes(parser):
invalid_json = (
'{task: "Research XAI", context: "Explainable AI", coworker: Senior Researcher}'
)
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_unclosed_brackets(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_extra_commas(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_trailing_commas(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_single_quotes(parser):
invalid_json = "{'task': 'Research XAI', 'context': 'Explainable AI', 'coworker': 'Senior Researcher'}"
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_mixed_quotes(parser):
invalid_json = "{'task': \"Research XAI\", 'context': \"Explainable AI\", 'coworker': 'Senior Researcher'}"
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_unescaped_characters(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher\n"}'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
print("result:", result)
assert result == expected_repaired_json
def test_safe_repair_json_missing_colon(parser):
invalid_json = '{"task" "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_missing_comma(parser):
invalid_json = '{"task": "Research XAI" "context": "Explainable AI", "coworker": "Senior Researcher"}'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_unexpected_trailing_characters(parser):
invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"} random text'
expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_safe_repair_json_special_characters_key(parser):
invalid_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
expected_repaired_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
result = parser._safe_repair_json(invalid_json)
assert result == expected_repaired_json
def test_parsing_with_whitespace(parser):
text = " Thought: Let's find the temperature \n Action: search \n Action Input: what is the temperature in SF? "
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is the temperature in SF?"
def test_parsing_with_special_characters(parser):
text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "what is the temperature in SF?"'
result = parser.parse(text)
assert isinstance(result, AgentAction)
assert result.tool == "search"
assert result.tool_input == "what is the temperature in SF?"
def test_integration_valid_and_invalid(parser):
text = """
Thought: Let's find the temperature
Action: search
Action Input: what is the temperature in SF?
Thought: I found the information
Final Answer: The temperature is 100 degrees
Thought: Missing action
Action Input: invalid
Thought: Missing action input
Action: invalid
"""
parts = text.strip().split("\n\n")
results = []
for part in parts:
try:
result = parser.parse(part.strip())
results.append(result)
except OutputParserException as e:
results.append(e)
assert isinstance(results[0], AgentAction)
assert isinstance(results[1], AgentFinish)
assert isinstance(results[2], OutputParserException)
assert isinstance(results[3], OutputParserException)
class MockAgent:
def increment_formatting_errors(self):
pass
# TODO: ADD TEST TO MAKE SURE ** REMOVAL DOESN'T MESS UP ANYTHING

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,151 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
specialized in technology, software engineering, AI and startups. You work as
a freelancer and is now working on doing research and analysis for a new customer.\nYour
personal goal is: Make the best research and analysis on content about AI and
AI agentsTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\nYour final answer must be the great and the most
complete as possible, it must be outcome described.\n\nI MUST use these formats,
my job depends on it!\nCurrent Task: Say Hi\n\nThis is the expect criteria for
your final answer: Hi \n you MUST return the actual complete content as the
final answer, not a summary.\n\nBegin! This is VERY important to you, use the
tools available and give your best Final Answer, your job depends on it!\n\nThought:\n",
"role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"], "stream":
true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1072'
content-type:
- application/json
cookie:
- _cfuvid=Nxp5RE8CN2EyHxMIvB_SaTizIH5w0eWt9SPilMuIjMk-1721227661802-0.0.1.1-604800000;
__cf_bm=jadAYV2gh7qPDzgKO9A4JzJTaI9c2fnnjxloIQZeOIw-1721227661-1.0.1.1-apaA8kQyGiEV3kOuXHe8z1zeyvxd_jBHCQpdqWirUlylrUo.uRZjRDueI.sSXS4hXoWkyIW6kIMt7lamQM2mdw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a4b087e7d024593-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 14:48:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '142'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999753'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_75100793afc289eaf8b56127e1cc0532
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,591 @@
interactions:
- request:
body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
with dog.\nYour personal goal is: Express hot takes on dog.To give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an analysis around dog.\n\nThis is the expect criteria for your
final answer: 1 bullet point about dog that''s under 15 words. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '951'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Dogs"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
are"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
incredibly"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
loyal"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
provide"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
unmatched"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
companionship"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
humans"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89d0fa4e7abf53db-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 02 Jul 2024 19:17:45 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=6Xl2nvdsXT4uSfQ3C1ZK.LWKGYekVs5ErrLDZOdI.50-1719947865-1.0.1.1-6RQoTCznxe7H868MoxghRegIZaElbG_bN_jbs94hmnsnuR1P9bptoj8o2DbOSvj48ubewyvy8L16mOZHlMLw_A;
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=kPTMOkGHQp0ytgVUrm3jFNiB9I.DDI2ONPRTr6IMTeo-1719947865623-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '102'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9997'
x-ratelimit-remaining-tokens:
- '15999783'
x-ratelimit-reset-requests:
- 14ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2c5219e228ce79f0131c497230904013
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are apple Researcher. You have a lot of
experience with apple.\nYour personal goal is: Express hot takes on apple.To
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\nYour final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!\nCurrent Task: Give me an analysis around apple.\n\nThis is the expect criteria
for your final answer: 1 bullet point about apple that''s under 15 words. \n
you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '961'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Apple"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
revolution"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"izes"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
technology"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
with"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
sleek"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
designs"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
seamless"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
integration"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
innovative"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
user"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
experiences"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89d0fa4e7ca907e6-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 02 Jul 2024 19:17:45 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=wf2ozMjr46sG0EhuZjpiDNagwTxC05ct3Hn7Y9Rs5AI-1719947865-1.0.1.1-uckxTTr7Yfe6sv4ZznqqrGTEz9E3_Cpp7OAWBIEeNz1Smdjwijw8YV5oYPe_6W4DrEtwVzRDxaqIHlWP55O0QA;
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=F9pWw4TeoPa8puOm5RN9Gp2oY0lRoN53ChZ1qFYx1S8-1719947865726-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '168'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9998'
x-ratelimit-remaining-tokens:
- '15999780'
x-ratelimit-reset-requests:
- 10ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e6dfeda5935eae030bcc2da526234635
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are cat Researcher. You have a lot of experience
with cat.\nYour personal goal is: Express hot takes on cat.To give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an analysis around cat.\n\nThis is the expect criteria for your
final answer: 1 bullet point about cat that''s under 15 words. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '951'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Cats"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
are"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
master"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ful"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
hunters"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
brilliant"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
problem"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-sol"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"vers"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89d0fa4e7ae912d7-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 02 Jul 2024 19:17:45 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=y7JNZ8WEp.q5pMXLi79ajfcI.F6MfE0GeYLw34Apkf0-1719947865-1.0.1.1-QKklGeYuOnsQROgqMs42XwqKNvW.mPrmcbtaxMnUg3eSgI7TRnRq4qPuSan0ynDt4Hd9NMuls2FR.Caa1MVr9Q;
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=FVQoSgcvVyiB_o43X6y5MGYgzGojmsQqS.nPObW3JYU-1719947865679-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '132'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999783'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a06bde4044d3ee75edf08f333139679c
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -1,314 +0,0 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
goal is: test goalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: just say hi!\n\nThis is
the expect criteria for your final answer: your greeting \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '853'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89c8c71ccad81823-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 01 Jul 2024 19:24:42 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=uU.2MR0L4Mv3xs4DzFlWOQLVId1dJXQBlWffhr9mqxU-1719861882-1.0.1.1-JSKN2_O9iYj8QCZjy0IGiunZxvXimz5Kzv5wQJedVua5E6WIl1UvP.wguXbK0cds7ayJReYnR8v8oAN2rmtnNQ;
path=/; expires=Mon, 01-Jul-24 19:54:42 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=yc5Q7WKbO5zoiGNQx86HpHNM3HeXi2HxCxw31lL_UuU-1719861882665-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '86'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999808'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_25d95f35048bf71e28d73fbed6576a6c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
goal is: test goalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: just say hello!\n\nThis
is the expect criteria for your final answer: your greeting \n you MUST return
the actual complete content as the final answer, not a summary.\n\nThis is the
context you''re working with:\nHi!\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '905'
content-type:
- application/json
cookie:
- __cf_bm=uU.2MR0L4Mv3xs4DzFlWOQLVId1dJXQBlWffhr9mqxU-1719861882-1.0.1.1-JSKN2_O9iYj8QCZjy0IGiunZxvXimz5Kzv5wQJedVua5E6WIl1UvP.wguXbK0cds7ayJReYnR8v8oAN2rmtnNQ;
_cfuvid=yc5Q7WKbO5zoiGNQx86HpHNM3HeXi2HxCxw31lL_UuU-1719861882665-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Hello"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89c8c7202e0f1823-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 01 Jul 2024 19:24:43 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '82'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999794'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_754b5067e8f56d5c1182dc0f57be0e45
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,258 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9hrsMKHuOkxqftWK9DtuC10VCJ17t","object":"chat.completion.chunk","created":1720242230,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89ed0cf0dc05741a-MIA
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Sat, 06 Jul 2024 05:03:50 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=JI76H4xxreAnMx1JJoPragplAdYdjbDNA68Hr3Cs_0k-1720242230-1.0.1.1-oHSrtm.ejkvCiAHC11lg0MnvmopYZayTZRq09IcH2yh5BA6FyyufGH7Rm59BAz.gdZHc0izmjElXfLiu2bZ_jQ;
path=/; expires=Sat, 06-Jul-24 05:33:50 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=X4.n0cNP9j1jseIPV4H1aDJu2xrsAwcUI8rY0tbLc40-1720242230210-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '71'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999772'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_8dc1d49d85fcf8e39601e32ca80abd6b
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=JI76H4xxreAnMx1JJoPragplAdYdjbDNA68Hr3Cs_0k-1720242230-1.0.1.1-oHSrtm.ejkvCiAHC11lg0MnvmopYZayTZRq09IcH2yh5BA6FyyufGH7Rm59BAz.gdZHc0izmjElXfLiu2bZ_jQ;
_cfuvid=X4.n0cNP9j1jseIPV4H1aDJu2xrsAwcUI8rY0tbLc40-1720242230210-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xSS2/bMAy++1cIPNeF81pT34YBG9A13aHAgL5gKArtKJVFTaKBtkH++yDFi91g
PggEP34PkN5nQoDeQClAbSWr1pn8euvD6id9OP3V3C6bzZ2qd7eT1f3DykgFF5FB6x0q/se6VNQ6
g6zJHmHlUTJG1cnVtJjOp9NZkYCWNmgirXGczymPYF4s8smsJ25JKwxQiqdMCCH26Y0R7QbfoBRJ
JnVaDEE2COVpSAjwZGIHZAg6sLQMFwOoyDLamNp2xowAJjKVksYMxsdvP6qHPUljqsI2duX13ePN
w2/7HT/+8Lfd45cfYeR3lH53KVDdWXXazwg/9cszMyHAyjZx7xV5/NWx6/iMLgRI33QtWo7RYf8M
IQ4/Qzk/wKfRQ/a/+qWvDqe1Gmqcp3U42xLU2uqwrTzKkNJCYHJHiyj3ks7XfboIOE+t44rpFW0U
XPbXg+F/GcBFjzGxNCPOIuvjQXgPjG1Va9ugd16nU0LtqnlRLHG2vppcQ3bI/gIAAP//AwCtLU45
0wIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89ed0cf40ebc741a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 06 Jul 2024 05:03:50 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '186'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5da164d15ccb331864aeb5d3562969aa
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,193 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
specialized in technology, software engineering, AI and startups. You work as
a freelancer and is now working on doing research and analysis for a new customer.\nYour
personal goal is: Make the best research and analysis on content about AI and
AI agentsTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\nYour final answer must be the great and the most
complete as possible, it must be outcome described.\n\nI MUST use these formats,
my job depends on it!\nCurrent Task: Look at the available data nd give me a
sense on the total number of sales.\n\nThis is the expect criteria for your
final answer: The total number of sales as an integer \n you MUST return the
actual complete content as the final answer, not a summary.\n\nBegin! This is
VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1178'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.34.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.34.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
The"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
total"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
number"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
sales"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
is"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"150"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"0"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9gJkkQs40FNqD9UjPrPbDEUN4XeLR","object":"chat.completion.chunk","created":1719872734,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 89c9d0107c8abd30-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 01 Jul 2024 22:25:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=xIvvDveyc7bpEywphx5N4EscKoZiGAT_yDVu3aFAWZ4-1719872735-1.0.1.1-ZOUYc2kEes8fxrMFgGdVppzOh9nPbl4y1Syv73ORt38FBXePWFSTJrFZCZRU.zob6ks9nWzr2vBIZbBQdAOOGQ;
path=/; expires=Mon, 01-Jul-24 22:55:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aG1BGRRkNAyxmctM98.DLqSNJ2Cx_OQYsMRQbd03.bo-1719872735091-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '80'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '16000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '15999725'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_c90015b7584729268f48a8b33ff7c5ea
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,262 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e81aa7f0c7e-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 07:35:41 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
path=/; expires=Wed, 17-Jul-24 08:05:41 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '106'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e52461a1ab2702e360f6303fbcb4cc3c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
_cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xS22rjMBB991eIeY6LHTubrR9LKYUttKWUvbUYRRnb6sqSVhqTJiH/vshxYzes
H8QwZ86FGe8jxkCuoWAgGk6itSq+VPR8d8O/vXXZbiOzx13S5D9/PNwSv8nvYBYYZvWGgj5YF8K0
ViFJo4+wcMgJg2q6nKfzJF3maQ+0Zo0q0GpLcW7ieTLP42QRp9lAbIwU6KFgvyPGGNv3b4io1/gO
BUtmH50Wvec1QnEaYgycUaED3HvpiWuC2QgKowl1SK07pSYAGaNKwZUajY/fflKPe+JKlVe/nqvV
98vNtslul3/Xj7vrzaZ6StOJ31F6a/tAVafFaT8T/NQvzswYA83bnvskjMP7jmxHZ3TGgLu6a1FT
iA77F/Bh+AWK/ACfRg/R/+rXoTqc1qpMbZ1Z+bMtQSW19E3pkPs+LXgy9mgR5F7783WfLgLWmdZS
SeYP6iD4dbgejP/LCC4GjAxxNeEsoiEe+K0nbMtK6hqddbI/JVS2FDkuVl8qnqUQHaJ/AAAA//8D
ACb4o2zTAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e858ca50c7e-EWR
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 17 Jul 2024 07:35:42 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '241'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999968'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_01c2f40fe9c73f883b7ed5b60c8067e5
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,192 @@
interactions:
- request:
body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
with dog.\nYour personal goal is: Express hot takes on dog.To give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an analysis around dog.\n\nThis is the expect criteria for your
final answer: 1 bullet point about dog that''s under 15 words. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '951'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
Dogs"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
are"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
unparalleled"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
loyalty"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
companionship"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
humans"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0959de6b916783-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 15:29:42 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=LA.xC.jE_aMjiSgGgU6kDsBPhb_akgqn_4Rx.jXYfnQ-1720538982-1.0.1.1-l5Q1BHprIz5Jxb4HWyYsMfbg6mEnP2H95Vxt89ez24pKOb__90s8LJBBqK52zmPNcPYSSUcaR0wRAaSVFoa4Fw;
path=/; expires=Tue, 09-Jul-24 15:59:42 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=zzJ51X.VwRkIq7VLCg9xPQGbXoUmAH6b.2g6sf6Y58Y-1720538982657-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '240'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999783'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_abdec68aded596628dfd5b999919447d
status:
code: 200
message: OK
version: 1

View File

@@ -1,296 +1,266 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n\nUse the following format:\n\nThought: you should always
think about what to do\nAction: the action to take, only one name of [multiplier],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n\n\nCurrent Task: What is 3 times 4?\n\nThis is the expect criteria
for your final answer: The result of the multiplication. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
goal is: test goal\nYou ONLY have access to the following tools, and should
NEVER make up tools that are not listed here:\n\nmultiplier(first_number: int,
second_number: int) -> float - Useful for when you need to multiply two numbers
together.\n\nUse the following format:\n\nThought: you should always think about
what to do\nAction: the action to take, only one name of [multiplier], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n\nCurrent Task: What is 3 times
4?\n\nThis is the expect criteria for your final answer: The result of the multiplication.
\n you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1277'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
need"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
determine"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
product"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
multiplier"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Input"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
{\""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"first"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
\""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"second"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"}"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a2345bd1ffd742e-MIA
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Fri, 12 Jul 2024 18:59:47 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=EvHnbspWLzEWYmRV1sLsvFlp1S5ePQd_KIGldEvula4-1720810787-1.0.1.1-fcfgfphTZearpEpqAdn5vCov8FO3hERf4Zij0dZmjoTuHkfcpXthynLGlq2sBt7SpE72ogziXHDlNZsSvmBQzA;
path=/; expires=Fri, 12-Jul-24 19:29:47 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=QoRToNVlfxPsZucAm6jmW5xUqoEucDbQTYK4SkSwmUc-1720810787746-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '90'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999703'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f9575c9cc6494a463ddd5681e599b56d
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
goal is: test goal\nYou ONLY have access to the following tools, and should
NEVER make up tools that are not listed here:\n\nmultiplier(first_number: int,
second_number: int) -> float - Useful for when you need to multiply two numbers
together.\n\nUse the following format:\n\nThought: you should always think about
what to do\nAction: the action to take, only one name of [multiplier], just
the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n\nCurrent Task: What is 3 times
4?\n\nThis is the expect criteria for your final answer: The result of the multiplication.
\n you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:\nI need to determine the product
of 3 and 4.\n\nAction: multiplier\nAction Input: {\"first_number\": 3, \"second_number\":
4}\nObservation: 12\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
- gzip, deflate
connection:
- keep-alive
content-length:
- '1268'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
need"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
calculate"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
product"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"multi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"plier"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
Input"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"{\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
\""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"first"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":",\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
\""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"second"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"}\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85e2ba970e5851e6-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Type:
- text/event-stream
Date:
- Sat, 02 Mar 2024 16:23:01 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=C0VdYjpV_Hv7CqW8v18fK47fudXVna82_U1z_FcZ1Ng-1709396581-1.0.1.1-3mcMHbUjGImAUy9c5jtpPwFU1NQDoziKGjF8PNiFaGvST9S6PAOQVvyo4vHhKkznZM38Rs39YASCuQyyHRlkUg;
path=/; expires=Sat, 02-Mar-24 16:53:01 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=XwSpHIa8bLFKjduTc6qVKOscgm9TIoxw5Nm7uklFgXw-1709396581628-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '360'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299706'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 58ms
x-request-id:
- req_e3515cf2ba7a535d68b03019b57dfbf1
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
personal goal is: test goal\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n\nUse the following format:\n\nThought: you should always
think about what to do\nAction: the action to take, only one name of [multiplier],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple a python dictionary using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n\n\nCurrent Task: What is 3 times 4?\n\nThis is the expect criteria
for your final answer: The result of the multiplication. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought: \nI need to calculate the product of 3 and
4.\n\nAction: \nmultiplier\n\nAction Input: \n{\n \"first_number\": 3,\n \"second_number\":
4\n}\n\nObservation: 12\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1428'
- '1420'
content-type:
- application/json
cookie:
- __cf_bm=C0VdYjpV_Hv7CqW8v18fK47fudXVna82_U1z_FcZ1Ng-1709396581-1.0.1.1-3mcMHbUjGImAUy9c5jtpPwFU1NQDoziKGjF8PNiFaGvST9S6PAOQVvyo4vHhKkznZM38Rs39YASCuQyyHRlkUg;
_cfuvid=XwSpHIa8bLFKjduTc6qVKOscgm9TIoxw5Nm7uklFgXw-1709396581628-0.0.1.1-604800000
- __cf_bm=EvHnbspWLzEWYmRV1sLsvFlp1S5ePQd_KIGldEvula4-1720810787-1.0.1.1-fcfgfphTZearpEpqAdn5vCov8FO3hERf4Zij0dZmjoTuHkfcpXthynLGlq2sBt7SpE72ogziXHDlNZsSvmBQzA;
_cfuvid=QoRToNVlfxPsZucAm6jmW5xUqoEucDbQTYK4SkSwmUc-1720810787746-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
@@ -300,7 +270,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
@@ -309,60 +279,60 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
string: 'data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
know"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"12"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"12"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
@@ -373,47 +343,41 @@ interactions:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85e2baa3593951e6-GRU
Cache-Control:
- no-cache, must-revalidate
- 8a2345c21e0b742e-MIA
Connection:
- keep-alive
Content-Type:
- text/event-stream
- text/event-stream; charset=utf-8
Date:
- Sat, 02 Mar 2024 16:23:03 GMT
- Fri, 12 Jul 2024 18:59:48 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '321'
- '133'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299670'
- '21999671'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 65ms
- 0s
x-request-id:
- req_5670da4792b11cfa6dd8ed3b6dd85cbc
- req_be7165ee4924469e40e6a6b89a758b39
status:
code: 200
message: OK

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,453 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f368ab6734-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:38 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
path=/; expires=Tue, 09-Jul-24 21:35:38 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '159'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a58604fe17d3de5d4491ec972e98312b
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
_cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xSTW/bMAy9+1cIPMeDncRL7Gt2GNJhOWzdDmthKIriqJFETaK7FkH++yDHjd2g
PggEH98HSJ8SxkDtoGIgDpyEcTotn1Zr8/1lvViV9+rY6ru/zhW/8i+HpvA/YRIZuH2Sgt5YnwQa
pyUptBdYeMlJRtV8Mc2Kosxnyw4wuJM60hpH6RzTaTadp1mR5rOeeEAlZICK/UkYY+zUvTGi3ckX
qFg2eesYGQJvJFTXIcbAo44d4CGoQNwSTAZQoCVpY2rbaj0CCFHXgms9GF++06ge9sS1rk3Y/Cvv
Nq75upx+Pj7/vsfnb2ta6ZHfRfrVdYH2rRXX/Yzwa7+6MWMMLDcd94dALzctuZZu6IwB901rpKUY
HU4PEOLwA1TzM7wbPScf1Y99db6uVWPjPG7DzZZgr6wKh9pLHrq0EAjdxSLKPXbna99dBJxH46gm
PEobBZf99WD4Xwaw6DFC4nrEKZI+HoTXQNLUe2Ub6Z1X3Slh7+p5li3lbLvIS0jOyX8AAAD//wMA
s5wGAdMCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f828146734-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:38 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '215'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_34b28faf23b6422bb0855e6a45c65e92
status:
code: 200
message: OK
- request:
body: '{"input": ["examples(Examples): Specific scenarios used to explain counting,
addition, and subtraction through the zoo theme, such as counting animals, adding
new ones, and subtracting adopted ones."], "model": "text-embedding-ada-002",
"encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '265'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f9bc6c4589-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:39 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=IuvCm3DYH_Yj2KCjQfa873zjAj_2TgaF47eD6tQ4Mhs-1720559139-1.0.1.1-fWDjNt6ARNNwSwU4ZoyX.VoMhynDVIi97V54zsXBMuMg_KjRGid.vTsH.YWP4cEbPWj_vdlZjnfl3ef4S90Eog;
path=/; expires=Tue, 09-Jul-24 21:35:39 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uolQOZ2C52Hd5W7TXNWyFaYk4FEIIwP0B2MH49GGYtA-1720559139009-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- text-embedding-ada-002
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '18'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999953'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5f80532d772393d55159f71cbd4e8211
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,258 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45eb19a3c00b-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
path=/; expires=Tue, 09-Jul-24 21:35:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '96'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ee2fc8fd37b03ee0bcf92ff34f91a51c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
_cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xS22rjMBB991eIeY4X5+K68WsoXbplt6WUQjfFKIp8SWSNkMabpiH/XuS4sRvW
D2KYM+fCjA8BY1CtIWUgSk6iNiqcbxZ3anfPy6sPnu92k23iVvttUl7/XPz+BSPPwNVGCvpi/RBY
GyWpQn2ChZWcpFcdJ5MojufjadICNa6l8rTCUDjDcBJNZmEUh+NpRyyxEtJByv4GjDF2aF8fUa/l
O6QsGn11aukcLySk5yHGwKLyHeDOVY64Jhj1oEBNUvvUulFqABCiygRXqjc+fYdB3e+JK5Wtdrc3
L83Y7h8Xm4/7l3/b13nx8Hz3MPA7Se9NGyhvtDjvZ4Cf++mFGWOged1ynwRa+ach09AFnTHgtmhq
qclHh8MSnB9eQjo7wrfRY/C/+q2rjue1KiyMxZW72BLkla5cmVnJXZsWHKE5WXi5t/Z8zbeLgLFY
G8oIt1J7wevuetD/Lz0YdxghcTXgxEEXD9zekayzvNKFtMZW7SkhN9k6Tq6mUZLPIwiOwScAAAD/
/wMAE8hqg9MCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45ef8871c00b-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:37 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '298'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cea16690999d7a4128fd55687dc31397
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,258 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45e24b19bd4d-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
path=/; expires=Tue, 09-Jul-24 21:35:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '105'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_759b74b995b84a531eae7df3eddf1196
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
_cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xS22rcMBB991eIeV4XX9ZJ1m8lEGgKSZtSUnLBKPLYq40sCWmcdFn234u8ztpZ
6gcxzJlzYca7iDGQNZQMxJqT6KyKV5vL680mzX58Xd4l773D7O63vMjP7rfrKwuLwDAvGxT0wfoi
TGcVkjT6AAuHnDCopudZUhSrNC8GoDM1qkBrLcVLE2dJtoyTIk7zkbg2UqCHkj1GjDG2G94QUdf4
F0qWLD46HXrPW4TyOMQYOKNCB7j30hPXBIsJFEYT6pBa90rNADJGVYIrNRkfvt2snvbElareb27S
b28/v7/VRXtP13X75+GMF+hmfgfprR0CNb0Wx/3M8GO/PDFjDDTvBu4vYRze9mR7OqEzBty1fYea
QnTYPYEPw09QLvfwaXQf/a9+Hqv9ca3KtNaZF3+yJWikln5dOeR+SAuejD1YBLnn4Xz9p4uAdaaz
VJF5RR0EL8brwfS/TGAxYmSIqxmniMZ44LeesKsaqVt01snhlNDYSmByvsrzPGkg2kf/AAAA//8D
AKtPZkLTAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45e5ffd7bd4d-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:36 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '153'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_36cd16b74a2085c72139d09309d21e39
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,697 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
specialized in technology, software engineering, AI and startups. You work as
a freelancer and is now working on doing research and analysis for a new customer.\nYour
personal goal is: Make the best research and analysis on content about AI and
AI agentsTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\nYour final answer must be the great and the most
complete as possible, it must be outcome described.\n\nI MUST use these formats,
my job depends on it!\nCurrent Task: Generate a list of 5 interesting ideas
to explore for an article, where each bulletpoint is under 15 words.\n\nThis
is the expect criteria for your final answer: Bullet point list of 5 important
events. No additional commentary. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1237'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Ethical"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
implications"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
decision"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-making"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
healthcare"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
agents"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
revolution"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"izing"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
customer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
service"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
e"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-commerce"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Advances"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-driven"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
predictive"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
maintenance"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
for"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
industries"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
The"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
role"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
autonomous"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
vehicle"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
safety"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
personalized"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
education"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Adaptive"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
learning"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
technologies"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a097b99ad909e50-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 15:52:44 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
path=/; expires=Tue, 09-Jul-24 16:22:44 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-soijsnuwuk3xvbf91w0jc33c
openai-processing-ms:
- '114'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '5000'
x-ratelimit-limit-tokens:
- '450000'
x-ratelimit-remaining-requests:
- '4999'
x-ratelimit-remaining-tokens:
- '449712'
x-ratelimit-reset-requests:
- 12ms
x-ratelimit-reset-tokens:
- 38ms
x-request-id:
- req_94f0907cc8b2065f1e223070d2be2a85
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
specialized in technology, software engineering, AI and startups. You work as
a freelancer and is now working on doing research and analysis for a new customer.\nYour
personal goal is: Make the best research and analysis on content about AI and
AI agentsTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\nYour final answer must be the great and the most
complete as possible, it must be outcome described.\n\nI MUST use these formats,
my job depends on it!\nCurrent Task: Generate a list of 5 interesting ideas
to explore for an article, where each bulletpoint is under 15 words.\n\nThis
is the expect criteria for your final answer: Bullet point list of 5 important
events. No additional commentary. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '1237'
content-type:
- application/json
cookie:
- __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
_cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Evolution"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Agents"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Customer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Service"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Healthcare"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Transform"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ing"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Diagnostics"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Treatment"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Ethical"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Imp"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"lications"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
of"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Autonomous"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Systems"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Driven"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Start"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ups"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Dis"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ruption"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Innovation"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
AI"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Cyber"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"security"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Def"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ending"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Against"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Modern"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Threat"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"s"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a097ba2bc449e50-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 15:52:45 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- user-soijsnuwuk3xvbf91w0jc33c
openai-processing-ms:
- '117'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '5000'
x-ratelimit-limit-tokens:
- '450000'
x-ratelimit-remaining-requests:
- '4999'
x-ratelimit-remaining-tokens:
- '449712'
x-ratelimit-reset-requests:
- 12ms
x-ratelimit-reset-tokens:
- 38ms
x-request-id:
- req_a28d912698f7b75be87900d3a64bc91f
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,161 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi to John \n you MUST return the
actual complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '918'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
John"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a2327f1190467c1-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Fri, 12 Jul 2024 18:39:27 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=df.hIcEr2QTS045wWa7HSF0ATx6AeLAoPPW0FoIx7W4-1720809567-1.0.1.1-1Y2nQ4DHdc5HUHFO08LdQOoWZykmQ0xe67vzmv2dS4OnnKEHYd9GMzcq.vWODTXoI.BoSxQiRrylKYuuO2t8Tw;
path=/; expires=Fri, 12-Jul-24 19:09:27 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Zmb0XRHa49q2R664FqlS3F.aojtATJKKGnkUiQoH92I-1720809567257-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '83'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999792'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4fd8c7c8d47e20be017fb8de1ccb07c9
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,159 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '910'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.14
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.14
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a488e7859304288-EWR
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Wed, 17 Jul 2024 07:35:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=tBullt04HIYduv1QEpAn86_ghx9PQ4DMe9LwLp7.bu4-1721201740-1.0.1.1-sGn3OYi9ntPGIzwuC4RH0UTUQFVy.BUFIvy9v9IrjorYeAsecsuuuREs7b19i4dXygWnZZEkH6cxvnQeJ62g7g;
path=/; expires=Wed, 17-Jul-24 08:05:40 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uSSEccAecytxcWKGJoaQXLVBAwHLrZ.QckpcK..rN48-1721201740355-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '83'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999793'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_89b4947eaf51788bd7a69d6cc0da6c08
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,472 @@
interactions:
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Context Task\n\nThis is
the expect criteria for your final answer: Say John \n you MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n":
1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '851'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Say"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
John"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a23033dc9abce48-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Fri, 12 Jul 2024 18:14:23 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
path=/; expires=Fri, 12-Jul-24 18:44:23 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '84'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999807'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e6b4b9610f2f254a228ad44dda349115
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi to John \n you MUST return the
actual complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nSay John\n\nBegin! This is VERY important to you, use
the tools available and give your best Final Answer, your job depends on it!\n\nThought:\n",
"role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"], "stream":
true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '908'
content-type:
- application/json
cookie:
- __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
_cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
John"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a230340ec4cce48-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Fri, 12 Jul 2024 18:14:24 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '69'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999795'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f3233314439a85e7a197be3d067c6d1c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
goal is: Test GoalTo give my best complete final answer to the task use the
exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
my best complete final answer to the task.\nYour final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
expect criteria for your final answer: Say Hi to John \n you MUST return the
actual complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\ncontext raw output\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, br
connection:
- keep-alive
content-length:
- '918'
content-type:
- application/json
cookie:
- __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
_cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.3
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.3
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
John"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a2303443f0cce48-SJC
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Fri, 12 Jul 2024 18:14:24 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '86'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999791'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_649687e24793d5b5782ecf58bc76386a
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,449 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, br
Connection:
- keep-alive
Content-Length:
- '23733'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.25.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 16 Jul 2024 18:43:12 GMT
status:
code: 200
message: OK
version: 1

Some files were not shown because too many files have changed in this diff Show More