mirror of
https://github.com/crewAIInc/crewAI.git
synced 2025-12-15 20:08:29 +00:00
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>
This commit is contained in:
Lorenze Jay
3
.gitignore
vendored
3
.gitignore
vendored
@@ -14,4 +14,5 @@ test.py
|
||||
rc-tests/*
|
||||
*.pkl
|
||||
temp/*
|
||||
.vscode/*
|
||||
.vscode/*
|
||||
crew_tasks_output.json
|
||||
@@ -156,3 +156,32 @@ 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.
|
||||
49
docs/how-to/Replay-tasks-from-latest-Crew-Kickoff.md
Normal file
49
docs/how-to/Replay-tasks-from-latest-Crew-Kickoff.md
Normal 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}")
|
||||
@@ -113,6 +113,11 @@ 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/AgentOps-Observability">
|
||||
Agent Monitoring with AgentOps
|
||||
|
||||
@@ -145,6 +145,7 @@ nav:
|
||||
- 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'
|
||||
- Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
|
||||
- Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
|
||||
- Tools Docs:
|
||||
|
||||
@@ -180,7 +180,7 @@ 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
|
||||
|
||||
|
||||
@@ -1,8 +1,14 @@
|
||||
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
|
||||
|
||||
|
||||
@click.group()
|
||||
@@ -48,5 +54,50 @@ 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)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
crewai()
|
||||
|
||||
24
src/crewai/cli/replay_from_task.py
Normal file
24
src/crewai/cli/replay_from_task.py
Normal 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)
|
||||
@@ -21,3 +21,13 @@ def train():
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"An error occurred while training the crew: {e}")
|
||||
|
||||
def replay_from_task():
|
||||
"""
|
||||
Replay the crew execution from a specific task.
|
||||
"""
|
||||
try:
|
||||
{{crew_name}}Crew().crew().replay_from_task(task_id=sys.argv[1])
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"An error occurred while replaying the crew: {e}")
|
||||
|
||||
@@ -11,6 +11,7 @@ crewai = { extras = ["tools"], version = "^0.35.8" }
|
||||
[tool.poetry.scripts]
|
||||
{{folder_name}} = "{{folder_name}}.main:run"
|
||||
train = "{{folder_name}}.main:train"
|
||||
replay = "{{folder_name}}.main:replay_from_task"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
|
||||
@@ -6,15 +6,15 @@ from typing import Any, Dict, List, Optional, Tuple, Union
|
||||
|
||||
from langchain_core.callbacks import BaseCallbackHandler
|
||||
from pydantic import (
|
||||
UUID4,
|
||||
BaseModel,
|
||||
ConfigDict,
|
||||
Field,
|
||||
InstanceOf,
|
||||
Json,
|
||||
PrivateAttr,
|
||||
field_validator,
|
||||
model_validator,
|
||||
UUID4,
|
||||
BaseModel,
|
||||
ConfigDict,
|
||||
Field,
|
||||
InstanceOf,
|
||||
Json,
|
||||
PrivateAttr,
|
||||
field_validator,
|
||||
model_validator,
|
||||
)
|
||||
from pydantic_core import PydanticCustomError
|
||||
|
||||
@@ -31,8 +31,13 @@ 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.task_output_storage_handler import TaskOutputStorageHandler
|
||||
|
||||
from crewai.utilities.formatter import (
|
||||
aggregate_raw_outputs_from_task_outputs,
|
||||
aggregate_raw_outputs_from_tasks,
|
||||
@@ -80,6 +85,13 @@ 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)
|
||||
@@ -135,6 +147,14 @@ class Crew(BaseModel):
|
||||
default=False,
|
||||
description="output_log_file",
|
||||
)
|
||||
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
|
||||
@@ -376,7 +396,11 @@ class Crew(BaseModel):
|
||||
) -> CrewOutput:
|
||||
"""Starts the crew to work on its assigned tasks."""
|
||||
self._execution_span = self._telemetry.crew_execution_span(self, 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()
|
||||
|
||||
@@ -403,7 +427,7 @@ class Crew(BaseModel):
|
||||
if self.process == Process.sequential:
|
||||
result = self._run_sequential_process()
|
||||
elif self.process == Process.hierarchical:
|
||||
result = self._run_hierarchical_process() # type: ignore # Incompatible types in assignment (expression has type "str | dict[str, Any]", variable has type "str")
|
||||
result = self._run_hierarchical_process()
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
f"The process '{self.process}' is not implemented yet."
|
||||
@@ -440,6 +464,7 @@ 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]] = {}) -> CrewOutput:
|
||||
@@ -488,129 +513,48 @@ class Crew(BaseModel):
|
||||
total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
|
||||
|
||||
self.usage_metrics = total_usage_metrics
|
||||
|
||||
self._task_output_handler.reset()
|
||||
return results
|
||||
|
||||
def _store_execution_log(
|
||||
self,
|
||||
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."""
|
||||
task_outputs: List[TaskOutput] = []
|
||||
futures: List[Tuple[Task, Future[TaskOutput]]] = []
|
||||
return self._execute_tasks(self.tasks)
|
||||
|
||||
for task in self.tasks:
|
||||
if task.agent and task.agent.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:
|
||||
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)
|
||||
|
||||
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"
|
||||
)
|
||||
|
||||
if task.async_execution:
|
||||
context = (
|
||||
aggregate_raw_outputs_from_tasks(task.context)
|
||||
if task.context
|
||||
else aggregate_raw_outputs_from_task_outputs(task_outputs)
|
||||
)
|
||||
future = task.execute_async(
|
||||
agent=task.agent, context=context, tools=task.tools
|
||||
)
|
||||
futures.append((task, future))
|
||||
else:
|
||||
# Before executing a synchronous task, wait for all async tasks to complete
|
||||
if futures:
|
||||
# Clear task_outputs before processing async tasks
|
||||
task_outputs = []
|
||||
for future_task, future in futures:
|
||||
task_output = future.result()
|
||||
task_outputs.append(task_output)
|
||||
self._process_task_result(future_task, task_output)
|
||||
|
||||
# Clear the futures list after processing all async results
|
||||
futures.clear()
|
||||
|
||||
context = (
|
||||
aggregate_raw_outputs_from_tasks(task.context)
|
||||
if task.context
|
||||
else aggregate_raw_outputs_from_task_outputs(task_outputs)
|
||||
)
|
||||
task_output = task.execute_sync(
|
||||
agent=task.agent, context=context, tools=task.tools
|
||||
)
|
||||
task_outputs = [task_output]
|
||||
self._process_task_result(task, task_output)
|
||||
|
||||
if futures:
|
||||
# Clear task_outputs before processing async tasks
|
||||
task_outputs = []
|
||||
for future_task, future in futures:
|
||||
task_output = future.result()
|
||||
task_outputs.append(task_output)
|
||||
self._process_task_result(future_task, task_output)
|
||||
|
||||
# Important: There should only be one task output in the list
|
||||
# If there are more or 0, something went wrong.
|
||||
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 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_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")
|
||||
|
||||
# TODO: @joao, Breaking change. Changed return type. Usage metrics is included in crewoutput
|
||||
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
|
||||
@@ -629,74 +573,148 @@ class Crew(BaseModel):
|
||||
)
|
||||
self.manager_agent = manager
|
||||
|
||||
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.
|
||||
|
||||
Args:
|
||||
tasks (List[Task]): List of tasks to execute
|
||||
manager (Optional[BaseAgent], optional): Manager agent to use for delegation. Defaults to None.
|
||||
|
||||
Returns:
|
||||
CrewOutput: Final output of the crew
|
||||
"""
|
||||
|
||||
task_outputs: List[TaskOutput] = []
|
||||
futures: List[Tuple[Task, Future[TaskOutput]]] = []
|
||||
futures: List[Tuple[Task, Future[TaskOutput], int]] = []
|
||||
last_sync_output: Optional[TaskOutput] = None
|
||||
|
||||
# TODO: IF USER OVERRIDE THE CONTEXT, PASS THAT
|
||||
for task in self.tasks:
|
||||
self._logger.log("debug", f"Working Agent: {manager.role}")
|
||||
self._logger.log("info", f"Starting Task: {task.description}")
|
||||
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
|
||||
|
||||
if self.output_log_file:
|
||||
self._file_handler.log(
|
||||
agent=manager.role, task=task.description, status="started"
|
||||
self._prepare_task(task, manager)
|
||||
if self.process == Process.hierarchical:
|
||||
agent_to_use = manager
|
||||
else:
|
||||
agent_to_use = task.agent
|
||||
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."
|
||||
)
|
||||
self._log_task_start(task, agent_to_use)
|
||||
|
||||
if task.async_execution:
|
||||
context = (
|
||||
aggregate_raw_outputs_from_tasks(task.context)
|
||||
if task.context
|
||||
else aggregate_raw_outputs_from_task_outputs(task_outputs)
|
||||
context = self._get_context(
|
||||
task, [last_sync_output] if last_sync_output else []
|
||||
)
|
||||
future = task.execute_async(
|
||||
agent=manager, context=context, tools=manager.tools
|
||||
agent=agent_to_use,
|
||||
context=context,
|
||||
tools=agent_to_use.tools,
|
||||
)
|
||||
futures.append((task, future))
|
||||
futures.append((task, future, task_index))
|
||||
else:
|
||||
# Before executing a synchronous task, wait for all async tasks to complete
|
||||
if futures:
|
||||
# Clear task_outputs before processing async tasks
|
||||
task_outputs = []
|
||||
for future_task, future in futures:
|
||||
task_output = future.result()
|
||||
task_outputs.append(task_output)
|
||||
self._process_task_result(future_task, task_output)
|
||||
|
||||
# Clear the futures list after processing all async results
|
||||
task_outputs.extend(
|
||||
self._process_async_tasks(futures, was_replayed)
|
||||
)
|
||||
futures.clear()
|
||||
|
||||
context = (
|
||||
aggregate_raw_outputs_from_tasks(task.context)
|
||||
if task.context
|
||||
else aggregate_raw_outputs_from_task_outputs(task_outputs)
|
||||
)
|
||||
context = self._get_context(task, task_outputs)
|
||||
task_output = task.execute_sync(
|
||||
agent=manager, context=context, tools=manager.tools
|
||||
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)
|
||||
|
||||
# Process any remaining async results
|
||||
if futures:
|
||||
# Clear task_outputs before processing async tasks
|
||||
task_outputs = []
|
||||
for future_task, future in futures:
|
||||
task_output = future.result()
|
||||
task_outputs.append(task_output)
|
||||
self._process_task_result(future_task, task_output)
|
||||
task_outputs = self._process_async_tasks(futures, was_replayed)
|
||||
|
||||
# Important: There should only be one task output in the list
|
||||
# If there are more or 0, something went wrong.
|
||||
return self._create_crew_output(task_outputs)
|
||||
|
||||
def _prepare_task(self, task: Task, manager: Optional[BaseAgent]):
|
||||
if self.process == Process.hierarchical:
|
||||
self._update_manager_tools(task, manager)
|
||||
elif task.agent and task.agent.allow_delegation:
|
||||
self._add_delegation_tools(task)
|
||||
|
||||
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, agent: Optional[BaseAgent]):
|
||||
color = self._logging_color
|
||||
role = agent.role if agent else "None"
|
||||
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: Optional[BaseAgent]):
|
||||
if task.agent and manager:
|
||||
manager.tools = task.agent.get_delegation_tools([task.agent])
|
||||
if manager:
|
||||
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 CrewOutput(
|
||||
@@ -707,6 +725,74 @@ class Crew(BaseModel):
|
||||
token_usage=token_usage,
|
||||
)
|
||||
|
||||
def _process_async_tasks(
|
||||
self,
|
||||
futures: List[Tuple[Task, Future[TaskOutput], int]],
|
||||
was_replayed: bool = False,
|
||||
) -> List[TaskOutput]:
|
||||
task_outputs = []
|
||||
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_from_task(
|
||||
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."""
|
||||
|
||||
|
||||
@@ -24,8 +24,6 @@ class CrewOutput(BaseModel):
|
||||
description="Processed token summary", default={}
|
||||
)
|
||||
|
||||
# TODO: Joao - Adding this safety check breakes when people want to see
|
||||
# The full output of a CrewOutput.
|
||||
# @property
|
||||
# def pydantic(self) -> Optional[BaseModel]:
|
||||
# # Check if the final task output included a pydantic model
|
||||
|
||||
166
src/crewai/memory/storage/kickoff_task_outputs_storage.py
Normal file
166
src/crewai/memory/storage/kickoff_task_outputs_storage.py
Normal 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",
|
||||
)
|
||||
@@ -204,6 +204,7 @@ class Task(BaseModel):
|
||||
tools: Optional[List[Any]],
|
||||
) -> TaskOutput:
|
||||
"""Run the core execution logic of the task."""
|
||||
self.agent = agent
|
||||
agent = agent or self.agent
|
||||
if not agent:
|
||||
raise Exception(
|
||||
@@ -244,7 +245,9 @@ class Task(BaseModel):
|
||||
content = (
|
||||
json_output
|
||||
if json_output
|
||||
else pydantic_output.model_dump_json() if pydantic_output else result
|
||||
else pydantic_output.model_dump_json()
|
||||
if pydantic_output
|
||||
else result
|
||||
)
|
||||
self._save_file(content)
|
||||
|
||||
@@ -378,7 +381,7 @@ class Task(BaseModel):
|
||||
def _convert_with_instructions(
|
||||
self, result: str, model: Type[BaseModel]
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
llm = self.agent.function_calling_llm or self.agent.llm
|
||||
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(
|
||||
|
||||
@@ -11,9 +11,7 @@ class TaskOutput(BaseModel):
|
||||
|
||||
description: str = Field(description="Description of the task")
|
||||
summary: Optional[str] = Field(description="Summary of the task", default=None)
|
||||
raw: str = Field(
|
||||
description="Raw output of the task", default=""
|
||||
) # TODO: @joao: breaking change, by renaming raw_output to raw, but now consistent with CrewOutput
|
||||
raw: str = Field(description="Raw output of the task", default="")
|
||||
pydantic: Optional[BaseModel] = Field(
|
||||
description="Pydantic output of task", default=None
|
||||
)
|
||||
@@ -32,8 +30,6 @@ class TaskOutput(BaseModel):
|
||||
self.summary = f"{excerpt}..."
|
||||
return self
|
||||
|
||||
# TODO: Joao - Adding this safety check breakes when people want to see
|
||||
# The full output of a TaskOutput or CrewOutput.
|
||||
# @property
|
||||
# def pydantic(self) -> Optional[BaseModel]:
|
||||
# # Check if the final task output included a pydantic model
|
||||
|
||||
31
src/crewai/utilities/crew_json_encoder.py
Normal file
31
src/crewai/utilities/crew_json_encoder.py
Normal 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
|
||||
@@ -1,5 +1,7 @@
|
||||
import os
|
||||
import pickle
|
||||
|
||||
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
|
||||
@@ -8,6 +8,8 @@ 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)
|
||||
else:
|
||||
print(content)
|
||||
|
||||
@@ -22,3 +24,6 @@ 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))
|
||||
|
||||
61
src/crewai/utilities/task_output_storage_handler.py
Normal file
61
src/crewai/utilities/task_output_storage_handler.py
Normal 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()
|
||||
File diff suppressed because it is too large
Load Diff
697
tests/cassettes/test_replay_feature.yaml
Normal file
697
tests/cassettes/test_replay_feature.yaml
Normal 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
|
||||
161
tests/cassettes/test_replay_from_task_setup_context.yaml
Normal file
161
tests/cassettes/test_replay_from_task_setup_context.yaml
Normal 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
|
||||
472
tests/cassettes/test_replay_interpolates_inputs_properly.yaml
Normal file
472
tests/cassettes/test_replay_interpolates_inputs_properly.yaml
Normal 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
|
||||
@@ -15,8 +15,10 @@ from crewai.crews.crew_output import CrewOutput
|
||||
from crewai.memory.contextual.contextual_memory import ContextualMemory
|
||||
from crewai.process import Process
|
||||
from crewai.task import Task
|
||||
from crewai.tasks.output_format import OutputFormat
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
from crewai.utilities import Logger, RPMController
|
||||
from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
|
||||
|
||||
ceo = Agent(
|
||||
role="CEO",
|
||||
@@ -136,7 +138,6 @@ def test_async_task_cannot_include_sequential_async_tasks_in_context():
|
||||
|
||||
|
||||
def test_context_no_future_tasks():
|
||||
|
||||
task2 = Task(
|
||||
description="Task 2",
|
||||
expected_output="output",
|
||||
@@ -584,7 +585,6 @@ def test_sequential_async_task_execution_completion():
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_single_task_with_async_execution():
|
||||
|
||||
researcher_agent = Agent(
|
||||
role="Researcher",
|
||||
goal="Make the best research and analysis on content about AI and AI agents",
|
||||
@@ -740,7 +740,6 @@ def test_async_task_execution_call_count():
|
||||
) as mock_execute_sync, patch.object(
|
||||
Task, "execute_async", return_value=mock_future
|
||||
) as mock_execute_async:
|
||||
|
||||
crew.kickoff()
|
||||
|
||||
assert mock_execute_async.call_count == 2
|
||||
@@ -1148,7 +1147,6 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_delegation_is_not_enabled_if_there_are_only_one_agent():
|
||||
|
||||
researcher = Agent(
|
||||
role="Researcher",
|
||||
goal="Make the best research and analysis on content about AI and AI agents",
|
||||
@@ -1238,10 +1236,10 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
|
||||
print(crew.usage_metrics)
|
||||
|
||||
assert crew.usage_metrics == {
|
||||
"total_tokens": 2217,
|
||||
"prompt_tokens": 1847,
|
||||
"completion_tokens": 370,
|
||||
"successful_requests": 4,
|
||||
"total_tokens": 311,
|
||||
"prompt_tokens": 224,
|
||||
"completion_tokens": 87,
|
||||
"successful_requests": 1,
|
||||
}
|
||||
|
||||
|
||||
@@ -1380,7 +1378,6 @@ def test_crew_does_not_interpolate_without_inputs():
|
||||
interpolate_task_inputs.assert_not_called()
|
||||
|
||||
|
||||
# TODO: Ask @joao if we want to start throwing errors if inputs are not provided
|
||||
# def test_crew_partial_inputs():
|
||||
# agent = Agent(
|
||||
# role="{topic} Researcher",
|
||||
@@ -1404,7 +1401,6 @@ def test_crew_does_not_interpolate_without_inputs():
|
||||
# assert crew.agents[0].backstory == "You have a lot of experience with AI."
|
||||
|
||||
|
||||
# TODO: If we do want ot throw errors if we are missing inputs. Add in this test.
|
||||
# def test_crew_invalid_inputs():
|
||||
# agent = Agent(
|
||||
# role="{topic} Researcher",
|
||||
@@ -1806,3 +1802,435 @@ def test__setup_for_training():
|
||||
|
||||
for agent in agents:
|
||||
assert agent.allow_delegation is False
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_replay_feature():
|
||||
list_ideas = Task(
|
||||
description="Generate a list of 5 interesting ideas to explore for an article, where each bulletpoint is under 15 words.",
|
||||
expected_output="Bullet point list of 5 important events. No additional commentary.",
|
||||
agent=researcher,
|
||||
)
|
||||
write = Task(
|
||||
description="Write a sentence about the events",
|
||||
expected_output="A sentence about the events",
|
||||
agent=writer,
|
||||
context=[list_ideas],
|
||||
)
|
||||
|
||||
crew = Crew(
|
||||
agents=[researcher, writer],
|
||||
tasks=[list_ideas, write],
|
||||
process=Process.sequential,
|
||||
)
|
||||
|
||||
with patch.object(Task, "execute_sync") as mock_execute_task:
|
||||
mock_execute_task.return_value = TaskOutput(
|
||||
description="Mock description",
|
||||
raw="Mocked output for list of ideas",
|
||||
agent="Researcher",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Mocked output for list of ideas",
|
||||
)
|
||||
|
||||
crew.kickoff()
|
||||
crew.replay_from_task(str(write.id))
|
||||
# Ensure context was passed correctly
|
||||
assert mock_execute_task.call_count == 3
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_crew_replay_from_task_error():
|
||||
task = Task(
|
||||
description="Come up with a list of 5 interesting ideas to explore for an article",
|
||||
expected_output="5 bullet points with a paragraph for each idea.",
|
||||
agent=researcher,
|
||||
)
|
||||
|
||||
crew = Crew(
|
||||
agents=[researcher, writer],
|
||||
tasks=[task],
|
||||
)
|
||||
|
||||
with pytest.raises(TypeError) as e:
|
||||
crew.replay_from_task() # type: ignore purposefully throwing err
|
||||
assert "task_id is required" in str(e)
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_crew_task_db_init():
|
||||
agent = Agent(
|
||||
role="Content Writer",
|
||||
goal="Write engaging content on various topics.",
|
||||
backstory="You have a background in journalism and creative writing.",
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Write a detailed article about AI in healthcare.",
|
||||
expected_output="A 1 paragraph article about AI.",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[task])
|
||||
|
||||
with patch.object(Task, "execute_sync") as mock_execute_task:
|
||||
mock_execute_task.return_value = TaskOutput(
|
||||
description="Write about AI in healthcare.",
|
||||
raw="Artificial Intelligence (AI) is revolutionizing healthcare by enhancing diagnostic accuracy, personalizing treatment plans, and streamlining administrative tasks.",
|
||||
agent="Content Writer",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Write about AI in healthcare...",
|
||||
)
|
||||
|
||||
crew.kickoff()
|
||||
|
||||
# Check if this runs without raising an exception
|
||||
try:
|
||||
db_handler = TaskOutputStorageHandler()
|
||||
db_handler.load()
|
||||
assert True # If we reach this point, no exception was raised
|
||||
except Exception as e:
|
||||
pytest.fail(f"An exception was raised: {str(e)}")
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_replay_task_with_context():
|
||||
agent1 = Agent(
|
||||
role="Researcher",
|
||||
goal="Research AI advancements.",
|
||||
backstory="You are an expert in AI research.",
|
||||
)
|
||||
agent2 = Agent(
|
||||
role="Writer",
|
||||
goal="Write detailed articles on AI.",
|
||||
backstory="You have a background in journalism and AI.",
|
||||
)
|
||||
|
||||
task1 = Task(
|
||||
description="Research the latest advancements in AI.",
|
||||
expected_output="A detailed report on AI advancements.",
|
||||
agent=agent1,
|
||||
)
|
||||
task2 = Task(
|
||||
description="Summarize the AI advancements report.",
|
||||
expected_output="A summary of the AI advancements report.",
|
||||
agent=agent2,
|
||||
)
|
||||
task3 = Task(
|
||||
description="Write an article based on the AI advancements summary.",
|
||||
expected_output="An article on AI advancements.",
|
||||
agent=agent2,
|
||||
)
|
||||
task4 = Task(
|
||||
description="Create a presentation based on the AI advancements article.",
|
||||
expected_output="A presentation on AI advancements.",
|
||||
agent=agent2,
|
||||
context=[task1],
|
||||
)
|
||||
|
||||
crew = Crew(
|
||||
agents=[agent1, agent2],
|
||||
tasks=[task1, task2, task3, task4],
|
||||
process=Process.sequential,
|
||||
)
|
||||
|
||||
mock_task_output1 = TaskOutput(
|
||||
description="Research the latest advancements in AI.",
|
||||
raw="Detailed report on AI advancements...",
|
||||
agent="Researcher",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Detailed report on AI advancements...",
|
||||
)
|
||||
mock_task_output2 = TaskOutput(
|
||||
description="Summarize the AI advancements report.",
|
||||
raw="Summary of the AI advancements report...",
|
||||
agent="Writer",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Summary of the AI advancements report...",
|
||||
)
|
||||
mock_task_output3 = TaskOutput(
|
||||
description="Write an article based on the AI advancements summary.",
|
||||
raw="Article on AI advancements...",
|
||||
agent="Writer",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Article on AI advancements...",
|
||||
)
|
||||
mock_task_output4 = TaskOutput(
|
||||
description="Create a presentation based on the AI advancements article.",
|
||||
raw="Presentation on AI advancements...",
|
||||
agent="Writer",
|
||||
json_dict=None,
|
||||
output_format=OutputFormat.RAW,
|
||||
pydantic=None,
|
||||
summary="Presentation on AI advancements...",
|
||||
)
|
||||
|
||||
with patch.object(Task, "execute_sync") as mock_execute_task:
|
||||
mock_execute_task.side_effect = [
|
||||
mock_task_output1,
|
||||
mock_task_output2,
|
||||
mock_task_output3,
|
||||
mock_task_output4,
|
||||
]
|
||||
|
||||
crew.kickoff()
|
||||
db_handler = TaskOutputStorageHandler()
|
||||
assert db_handler.load() != []
|
||||
|
||||
with patch.object(Task, "execute_sync") as mock_replay_task:
|
||||
mock_replay_task.return_value = mock_task_output4
|
||||
|
||||
replayed_output = crew.replay_from_task(str(task4.id))
|
||||
assert replayed_output.raw == "Presentation on AI advancements..."
|
||||
|
||||
db_handler.reset()
|
||||
|
||||
|
||||
def test_replay_from_task_with_context():
|
||||
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
|
||||
task1 = Task(
|
||||
description="Context Task", expected_output="Say Task Output", agent=agent
|
||||
)
|
||||
task2 = Task(
|
||||
description="Test Task", expected_output="Say Hi", agent=agent, context=[task1]
|
||||
)
|
||||
|
||||
context_output = TaskOutput(
|
||||
description="Context Task Output",
|
||||
agent="test_agent",
|
||||
raw="context raw output",
|
||||
pydantic=None,
|
||||
json_dict={},
|
||||
output_format=OutputFormat.RAW,
|
||||
)
|
||||
task1.output = context_output
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
|
||||
|
||||
with patch(
|
||||
"crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
|
||||
return_value=[
|
||||
{
|
||||
"task_id": str(task1.id),
|
||||
"output": {
|
||||
"description": context_output.description,
|
||||
"summary": context_output.summary,
|
||||
"raw": context_output.raw,
|
||||
"pydantic": context_output.pydantic,
|
||||
"json_dict": context_output.json_dict,
|
||||
"output_format": context_output.output_format,
|
||||
"agent": context_output.agent,
|
||||
},
|
||||
"inputs": {},
|
||||
},
|
||||
{
|
||||
"task_id": str(task2.id),
|
||||
"output": {
|
||||
"description": "Test Task Output",
|
||||
"summary": None,
|
||||
"raw": "test raw output",
|
||||
"pydantic": None,
|
||||
"json_dict": {},
|
||||
"output_format": "json",
|
||||
"agent": "test_agent",
|
||||
},
|
||||
"inputs": {},
|
||||
},
|
||||
],
|
||||
):
|
||||
crew.replay_from_task(str(task2.id))
|
||||
|
||||
assert crew.tasks[1].context[0].output.raw == "context raw output"
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_replay_with_invalid_task_id():
|
||||
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
|
||||
task1 = Task(
|
||||
description="Context Task", expected_output="Say Task Output", agent=agent
|
||||
)
|
||||
task2 = Task(
|
||||
description="Test Task", expected_output="Say Hi", agent=agent, context=[task1]
|
||||
)
|
||||
|
||||
context_output = TaskOutput(
|
||||
description="Context Task Output",
|
||||
agent="test_agent",
|
||||
raw="context raw output",
|
||||
pydantic=None,
|
||||
json_dict={},
|
||||
output_format=OutputFormat.RAW,
|
||||
)
|
||||
task1.output = context_output
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
|
||||
|
||||
with patch(
|
||||
"crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
|
||||
return_value=[
|
||||
{
|
||||
"task_id": str(task1.id),
|
||||
"output": {
|
||||
"description": context_output.description,
|
||||
"summary": context_output.summary,
|
||||
"raw": context_output.raw,
|
||||
"pydantic": context_output.pydantic,
|
||||
"json_dict": context_output.json_dict,
|
||||
"output_format": context_output.output_format,
|
||||
"agent": context_output.agent,
|
||||
},
|
||||
"inputs": {},
|
||||
},
|
||||
{
|
||||
"task_id": str(task2.id),
|
||||
"output": {
|
||||
"description": "Test Task Output",
|
||||
"summary": None,
|
||||
"raw": "test raw output",
|
||||
"pydantic": None,
|
||||
"json_dict": {},
|
||||
"output_format": "json",
|
||||
"agent": "test_agent",
|
||||
},
|
||||
"inputs": {},
|
||||
},
|
||||
],
|
||||
):
|
||||
with pytest.raises(
|
||||
ValueError,
|
||||
match="Task with id bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d not found in the crew's tasks.",
|
||||
):
|
||||
crew.replay_from_task("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
|
||||
|
||||
|
||||
@patch.object(Crew, "_interpolate_inputs")
|
||||
def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
|
||||
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
|
||||
task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
|
||||
task2 = Task(
|
||||
description="Test Task",
|
||||
expected_output="Say Hi to {name}",
|
||||
agent=agent,
|
||||
context=[task1],
|
||||
)
|
||||
|
||||
context_output = TaskOutput(
|
||||
description="Context Task Output",
|
||||
agent="test_agent",
|
||||
raw="context raw output",
|
||||
pydantic=None,
|
||||
json_dict={},
|
||||
output_format=OutputFormat.RAW,
|
||||
)
|
||||
task1.output = context_output
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
|
||||
crew.kickoff(inputs={"name": "John"})
|
||||
|
||||
with patch(
|
||||
"crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
|
||||
return_value=[
|
||||
{
|
||||
"task_id": str(task1.id),
|
||||
"output": {
|
||||
"description": context_output.description,
|
||||
"summary": context_output.summary,
|
||||
"raw": context_output.raw,
|
||||
"pydantic": context_output.pydantic,
|
||||
"json_dict": context_output.json_dict,
|
||||
"output_format": context_output.output_format,
|
||||
"agent": context_output.agent,
|
||||
},
|
||||
"inputs": {"name": "John"},
|
||||
},
|
||||
{
|
||||
"task_id": str(task2.id),
|
||||
"output": {
|
||||
"description": "Test Task Output",
|
||||
"summary": None,
|
||||
"raw": "test raw output",
|
||||
"pydantic": None,
|
||||
"json_dict": {},
|
||||
"output_format": "json",
|
||||
"agent": "test_agent",
|
||||
},
|
||||
"inputs": {"name": "John"},
|
||||
},
|
||||
],
|
||||
):
|
||||
crew.replay_from_task(str(task2.id))
|
||||
assert crew._inputs == {"name": "John"}
|
||||
assert mock_interpolate_inputs.call_count == 2
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_replay_from_task_setup_context():
|
||||
agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
|
||||
task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
|
||||
task2 = Task(
|
||||
description="Test Task",
|
||||
expected_output="Say Hi to {name}",
|
||||
agent=agent,
|
||||
)
|
||||
context_output = TaskOutput(
|
||||
description="Context Task Output",
|
||||
agent="test_agent",
|
||||
raw="context raw output",
|
||||
pydantic=None,
|
||||
json_dict={},
|
||||
output_format=OutputFormat.RAW,
|
||||
)
|
||||
task1.output = context_output
|
||||
crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
|
||||
with patch(
|
||||
"crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
|
||||
return_value=[
|
||||
{
|
||||
"task_id": str(task1.id),
|
||||
"output": {
|
||||
"description": context_output.description,
|
||||
"summary": context_output.summary,
|
||||
"raw": context_output.raw,
|
||||
"pydantic": context_output.pydantic,
|
||||
"json_dict": context_output.json_dict,
|
||||
"output_format": context_output.output_format,
|
||||
"agent": context_output.agent,
|
||||
},
|
||||
"inputs": {"name": "John"},
|
||||
},
|
||||
{
|
||||
"task_id": str(task2.id),
|
||||
"output": {
|
||||
"description": "Test Task Output",
|
||||
"summary": None,
|
||||
"raw": "test raw output",
|
||||
"pydantic": None,
|
||||
"json_dict": {},
|
||||
"output_format": "json",
|
||||
"agent": "test_agent",
|
||||
},
|
||||
"inputs": {"name": "John"},
|
||||
},
|
||||
],
|
||||
):
|
||||
crew.replay_from_task(str(task2.id))
|
||||
|
||||
# Check if the first task's output was set correctly
|
||||
assert crew.tasks[0].output is not None
|
||||
assert isinstance(crew.tasks[0].output, TaskOutput)
|
||||
assert crew.tasks[0].output.description == "Context Task Output"
|
||||
assert crew.tasks[0].output.agent == "test_agent"
|
||||
assert crew.tasks[0].output.raw == "context raw output"
|
||||
assert crew.tasks[0].output.output_format == OutputFormat.RAW
|
||||
|
||||
assert crew.tasks[1].prompt_context == "context raw output"
|
||||
|
||||
@@ -81,7 +81,7 @@ def test_task_prompt_includes_expected_output():
|
||||
|
||||
with patch.object(Agent, "execute_task") as execute:
|
||||
execute.return_value = "ok"
|
||||
task.execute_sync()
|
||||
task.execute_sync(agent=researcher)
|
||||
execute.assert_called_once_with(task=task, context=None, tools=[])
|
||||
|
||||
|
||||
@@ -104,7 +104,7 @@ def test_task_callback():
|
||||
|
||||
with patch.object(Agent, "execute_task") as execute:
|
||||
execute.return_value = "ok"
|
||||
task.execute_sync()
|
||||
task.execute_sync(agent=researcher)
|
||||
task_completed.assert_called_once_with(task.output)
|
||||
|
||||
|
||||
@@ -129,7 +129,7 @@ def test_task_callback_returns_task_ouput():
|
||||
|
||||
with patch.object(Agent, "execute_task") as execute:
|
||||
execute.return_value = "exported_ok"
|
||||
task.execute_sync()
|
||||
task.execute_sync(agent=researcher)
|
||||
# Ensure the callback is called with a TaskOutput object serialized to JSON
|
||||
task_completed.assert_called_once()
|
||||
callback_data = task_completed.call_args[0][0]
|
||||
@@ -521,9 +521,7 @@ def test_save_task_json_output():
|
||||
with patch.object(Task, "_save_file") as save_file:
|
||||
save_file.return_value = None
|
||||
crew.kickoff()
|
||||
save_file.assert_called_once_with(
|
||||
{"score": 4}
|
||||
) # TODO: @Joao, should this be a dict or a json string?
|
||||
save_file.assert_called_once_with({"score": 4})
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
|
||||
Reference in New Issue
Block a user