mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 15:48:29 +00:00
Merge branch 'pr-847' into lj/conditional-tasks-feat
This commit is contained in:
Lorenze Jay
3
.gitignore
vendored
3
.gitignore
vendored
@@ -13,4 +13,5 @@ db/
|
||||
test.py
|
||||
rc-tests/*
|
||||
*.pkl
|
||||
temp/*
|
||||
temp/*
|
||||
.vscode/*
|
||||
@@ -16,24 +16,24 @@ description: What are crewAI Agents and how to use them.
|
||||
|
||||
## Agent Attributes
|
||||
|
||||
| Attribute | Description |
|
||||
| :------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| **Role** | Defines the agent's function within the crew. It determines the kind of tasks the agent is best suited for. |
|
||||
| **Goal** | The individual objective that the agent aims to achieve. It guides the agent's decision-making process. |
|
||||
| **Backstory** | Provides context to the agent's role and goal, enriching the interaction and collaboration dynamics. |
|
||||
| **LLM** *(optional)* | Represents the language model that will run the agent. It dynamically fetches the model name from the `OPENAI_MODEL_NAME` environment variable, defaulting to "gpt-4" if not specified. |
|
||||
| **Tools** *(optional)* | Set of capabilities or functions that the agent can use to perform tasks. Expected to be instances of custom classes compatible with the agent's execution environment. Tools are initialized with a default value of an empty list. |
|
||||
| **Function Calling LLM** *(optional)* | Specifies the language model that will handle the tool calling for this agent, overriding the crew function calling LLM if passed. Default is `None`. |
|
||||
| **Max Iter** *(optional)* | `max_iter` is the maximum number of iterations the agent can perform before being forced to give its best answer. Default is `25`. |
|
||||
| **Max RPM** *(optional)* | `max_rpm` is Tte maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`. |
|
||||
| **Max Execution Time** *(optional)* | `max_execution_time` is the Maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time. |
|
||||
| **Verbose** *(optional)* | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`. |
|
||||
| **Allow Delegation** *(optional)* | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `True`. |
|
||||
| **Step Callback** *(optional)* | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`. |
|
||||
| **Cache** *(optional)* | Indicates if the agent should use a cache for tool usage. Default is `True`. |
|
||||
| **System Template** *(optional)* | Specifies the system format for the agent. Default is `None`. |
|
||||
| **Prompt Template** *(optional)* | Specifies the prompt format for the agent. Default is `None`. |
|
||||
| **Response Template** *(optional)* | Specifies the response format for the agent. Default is `None`. |
|
||||
| Attribute | Parameter | Description |
|
||||
| :------------------------- | :---- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| **Role** | `role` | Defines the agent's function within the crew. It determines the kind of tasks the agent is best suited for. |
|
||||
| **Goal** | `goal` | The individual objective that the agent aims to achieve. It guides the agent's decision-making process. |
|
||||
| **Backstory** | `backstory` | Provides context to the agent's role and goal, enriching the interaction and collaboration dynamics. |
|
||||
| **LLM** *(optional)* | `llm` | Represents the language model that will run the agent. It dynamically fetches the model name from the `OPENAI_MODEL_NAME` environment variable, defaulting to "gpt-4" if not specified. |
|
||||
| **Tools** *(optional)* | `tools` | Set of capabilities or functions that the agent can use to perform tasks. Expected to be instances of custom classes compatible with the agent's execution environment. Tools are initialized with a default value of an empty list. |
|
||||
| **Function Calling LLM** *(optional)* | `function_calling_llm` | Specifies the language model that will handle the tool calling for this agent, overriding the crew function calling LLM if passed. Default is `None`. |
|
||||
| **Max Iter** *(optional)* | `max_iter` | Max Iter is the maximum number of iterations the agent can perform before being forced to give its best answer. Default is `25`. |
|
||||
| **Max RPM** *(optional)* | `max_rpm` | Max RPM is the maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`. |
|
||||
| **Max Execution Time** *(optional)* | `max_execution_time` | Max Execution Time is the Maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time. |
|
||||
| **Verbose** *(optional)* | `verbose` | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`. |
|
||||
| **Allow Delegation** *(optional)* | `allow_delegation` | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `True`. |
|
||||
| **Step Callback** *(optional)* | `step_callback` | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`. |
|
||||
| **Cache** *(optional)* | `cache` | Indicates if the agent should use a cache for tool usage. Default is `True`. |
|
||||
| **System Template** *(optional)* | `system_template` | Specifies the system format for the agent. Default is `None`. |
|
||||
| **Prompt Template** *(optional)* | `prompt_template` | Specifies the prompt format for the agent. Default is `None`. |
|
||||
| **Response Template** *(optional)* | `response_template` | Specifies the response format for the agent. Default is `None`. |
|
||||
|
||||
## Creating an Agent
|
||||
|
||||
|
||||
@@ -8,29 +8,29 @@ A crew in crewAI represents a collaborative group of agents working together to
|
||||
|
||||
## Crew Attributes
|
||||
|
||||
| Attribute | Description |
|
||||
| :-------------------------- | :----------------------------------------------------------- |
|
||||
| **Tasks** | A list of tasks assigned to the crew. |
|
||||
| **Agents** | A list of agents that are part of the crew. |
|
||||
| **Process** *(optional)* | The process flow (e.g., sequential, hierarchical) the crew follows. |
|
||||
| **Verbose** *(optional)* | The verbosity level for logging during execution. |
|
||||
| **Manager LLM** *(optional)*| The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
|
||||
| **Function Calling LLM** *(optional)* | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
|
||||
| **Config** *(optional)* | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
|
||||
| **Max RPM** *(optional)* | Maximum requests per minute the crew adheres to during execution. |
|
||||
| **Language** *(optional)* | Language used for the crew, defaults to English. |
|
||||
| **Language File** *(optional)* | Path to the language file to be used for the crew. |
|
||||
| **Memory** *(optional)* | Utilized for storing execution memories (short-term, long-term, entity memory). |
|
||||
| **Cache** *(optional)* | Specifies whether to use a cache for storing the results of tools' execution. |
|
||||
| **Embedder** *(optional)* | Configuration for the embedder to be used by the crew. Mostly used by memory for now. |
|
||||
| **Full Output** *(optional)*| Whether the crew should return the full output with all tasks outputs or just the final output. |
|
||||
| **Step Callback** *(optional)* | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
|
||||
| **Task Callback** *(optional)* | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
|
||||
| **Share Crew** *(optional)* | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
|
||||
| **Output Log File** *(optional)* | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
|
||||
| **Manager Agent** *(optional)* | `manager` sets a custom agent that will be used as a manager. |
|
||||
| **Manager Callbacks** *(optional)* | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
|
||||
| **Prompt File** *(optional)* | Path to the prompt JSON file to be used for the crew. |
|
||||
| Attribute | Parameters | Description |
|
||||
| :-------------------------- | :------------------ | :------------------------------------------------------------------------------------------------------- |
|
||||
| **Tasks** | `tasks` | A list of tasks assigned to the crew. |
|
||||
| **Agents** | `agents` | A list of agents that are part of the crew. |
|
||||
| **Process** *(optional)* | `process` | The process flow (e.g., sequential, hierarchical) the crew follows. |
|
||||
| **Verbose** *(optional)* | `verbose` | The verbosity level for logging during execution. |
|
||||
| **Manager LLM** *(optional)*| `manager_llm` | The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
|
||||
| **Function Calling LLM** *(optional)* | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
|
||||
| **Config** *(optional)* | `config` | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
|
||||
| **Max RPM** *(optional)* | `max_rpm` | Maximum requests per minute the crew adheres to during execution. |
|
||||
| **Language** *(optional)* | `language` | Language used for the crew, defaults to English. |
|
||||
| **Language File** *(optional)* | `language_file` | Path to the language file to be used for the crew. |
|
||||
| **Memory** *(optional)* | `memory` | Utilized for storing execution memories (short-term, long-term, entity memory). |
|
||||
| **Cache** *(optional)* | `cache` | Specifies whether to use a cache for storing the results of tools' execution. |
|
||||
| **Embedder** *(optional)* | `embedder` | Configuration for the embedder to be used by the crew. Mostly used by memory for now. |
|
||||
| **Full Output** *(optional)*| `full_output` | Whether the crew should return the full output with all tasks outputs or just the final output. |
|
||||
| **Step Callback** *(optional)* | `step_callback` | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
|
||||
| **Task Callback** *(optional)* | `task_callback` | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
|
||||
| **Share Crew** *(optional)* | `share_crew` | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
|
||||
| **Output Log File** *(optional)* | `output_log_file` | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
|
||||
| **Manager Agent** *(optional)* | `manager_agent` | `manager` sets a custom agent that will be used as a manager. |
|
||||
| **Manager Callbacks** *(optional)* | `manager_callbacks` | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
|
||||
| **Prompt File** *(optional)* | `prompt_file` | Path to the prompt JSON file to be used for the crew. |
|
||||
|
||||
!!! note "Crew Max RPM"
|
||||
The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
|
||||
|
||||
@@ -11,20 +11,20 @@ Tasks within crewAI can be collaborative, requiring multiple agents to work toge
|
||||
|
||||
## Task Attributes
|
||||
|
||||
| Attribute | Description |
|
||||
| :----------------------| :-------------------------------------------------------------------------------------------- |
|
||||
| **Description** | A clear, concise statement of what the task entails. |
|
||||
| **Agent** | The agent responsible for the task, assigned either directly or by the crew's process. |
|
||||
| **Expected Output** | A detailed description of what the task's completion looks like. |
|
||||
| **Tools** *(optional)* | The functions or capabilities the agent can utilize to perform the task. |
|
||||
| **Async Execution** *(optional)* | If set, the task executes asynchronously, allowing progression without waiting for completion.|
|
||||
| **Context** *(optional)* | Specifies tasks whose outputs are used as context for this task. |
|
||||
| **Config** *(optional)* | Additional configuration details for the agent executing the task, allowing further customization. |
|
||||
| **Output JSON** *(optional)* | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set. |
|
||||
| **Output Pydantic** *(optional)* | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
|
||||
| **Output File** *(optional)* | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
|
||||
| **Callback** *(optional)* | A Python callable that is executed with the task's output upon completion. |
|
||||
| **Human Input** *(optional)* | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
|
||||
| Attribute | Parameters | Description |
|
||||
| :----------------------| :------------------- | :-------------------------------------------------------------------------------------------- |
|
||||
| **Description** | `description` | A clear, concise statement of what the task entails. |
|
||||
| **Agent** | `agent` | The agent responsible for the task, assigned either directly or by the crew's process. |
|
||||
| **Expected Output** | `expected_output` | A detailed description of what the task's completion looks like. |
|
||||
| **Tools** *(optional)* | `tools` | The functions or capabilities the agent can utilize to perform the task. |
|
||||
| **Async Execution** *(optional)* | `async_execution` | If set, the task executes asynchronously, allowing progression without waiting for completion.|
|
||||
| **Context** *(optional)* | `context` | Specifies tasks whose outputs are used as context for this task. |
|
||||
| **Config** *(optional)* | `config` | Additional configuration details for the agent executing the task, allowing further customization. |
|
||||
| **Output JSON** *(optional)* | `output_json` | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set. |
|
||||
| **Output Pydantic** *(optional)* | `output_pydantic` | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
|
||||
| **Output File** *(optional)* | `output_file` | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
|
||||
| **Callback** *(optional)* | `callback` | A Python callable that is executed with the task's output upon completion. |
|
||||
| **Human Input** *(optional)* | `human_input` | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
|
||||
|
||||
## Creating a Task
|
||||
|
||||
|
||||
@@ -37,10 +37,9 @@ writer = Agent(
|
||||
backstory='A skilled writer with a talent for crafting compelling narratives'
|
||||
)
|
||||
|
||||
# Define the tasks in sequence
|
||||
research_task = Task(description='Gather relevant data...', agent=researcher)
|
||||
analysis_task = Task(description='Analyze the data...', agent=analyst)
|
||||
writing_task = Task(description='Compose the report...', agent=writer)
|
||||
research_task = Task(description='Gather relevant data...', agent=researcher, expected_output='Raw Data')
|
||||
analysis_task = Task(description='Analyze the data...', agent=analyst, expected_output='Data Insights')
|
||||
writing_task = Task(description='Compose the report...', agent=writer, expected_output='Final Report')
|
||||
|
||||
# Form the crew with a sequential process
|
||||
report_crew = Crew(
|
||||
@@ -83,4 +82,4 @@ CrewAI tracks token usage across all tasks and agents. You can access these metr
|
||||
1. **Order Matters**: Arrange tasks in a logical sequence where each task builds upon the previous one.
|
||||
2. **Clear Task Descriptions**: Provide detailed descriptions for each task to guide the agents effectively.
|
||||
3. **Appropriate Agent Selection**: Match agents' skills and roles to the requirements of each task.
|
||||
4. **Use Context**: Leverage the context from previous tasks to inform subsequent ones
|
||||
4. **Use Context**: Leverage the context from previous tasks to inform subsequent ones
|
||||
|
||||
@@ -26,10 +26,12 @@ click = "^8.1.7"
|
||||
python-dotenv = "^1.0.0"
|
||||
appdirs = "^1.4.4"
|
||||
jsonref = "^1.1.0"
|
||||
agentops = { version = "^0.1.9", optional = true }
|
||||
embedchain = "^0.1.113"
|
||||
|
||||
[tool.poetry.extras]
|
||||
tools = ["crewai-tools"]
|
||||
agentops = ["agentops"]
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
isort = "^5.13.2"
|
||||
@@ -60,4 +62,4 @@ exclude = ["cli/templates/main.py", "cli/templates/crew.py"]
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
|
||||
@@ -18,7 +18,20 @@ from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_F
|
||||
from crewai.utilities.token_counter_callback import TokenCalcHandler
|
||||
from crewai.utilities.training_handler import CrewTrainingHandler
|
||||
|
||||
agentops = None
|
||||
try:
|
||||
import agentops
|
||||
from agentops import track_agent
|
||||
except ImportError:
|
||||
|
||||
def track_agent():
|
||||
def noop(f):
|
||||
return f
|
||||
|
||||
return noop
|
||||
|
||||
|
||||
@track_agent()
|
||||
class Agent(BaseAgent):
|
||||
"""Represents an agent in a system.
|
||||
|
||||
@@ -47,6 +60,8 @@ class Agent(BaseAgent):
|
||||
default=None,
|
||||
description="Maximum execution time for an agent to execute a task",
|
||||
)
|
||||
agent_ops_agent_name: str = None
|
||||
agent_ops_agent_id: str = None
|
||||
cache_handler: InstanceOf[CacheHandler] = Field(
|
||||
default=None, description="An instance of the CacheHandler class."
|
||||
)
|
||||
@@ -82,6 +97,7 @@ class Agent(BaseAgent):
|
||||
def __init__(__pydantic_self__, **data):
|
||||
config = data.pop("config", {})
|
||||
super().__init__(**config, **data)
|
||||
__pydantic_self__.agent_ops_agent_name = __pydantic_self__.role
|
||||
|
||||
@model_validator(mode="after")
|
||||
def set_agent_executor(self) -> "Agent":
|
||||
@@ -99,6 +115,12 @@ class Agent(BaseAgent):
|
||||
):
|
||||
self.llm.callbacks.append(token_handler)
|
||||
|
||||
if agentops and not any(
|
||||
isinstance(handler, agentops.LangchainCallbackHandler) for handler in self.llm.callbacks
|
||||
):
|
||||
agentops.stop_instrumenting()
|
||||
self.llm.callbacks.append(agentops.LangchainCallbackHandler())
|
||||
|
||||
if not self.agent_executor:
|
||||
if not self.cache_handler:
|
||||
self.cache_handler = CacheHandler()
|
||||
|
||||
@@ -15,8 +15,9 @@ from pydantic import (
|
||||
)
|
||||
from pydantic_core import PydanticCustomError
|
||||
|
||||
from crewai.agents import CacheHandler, ToolsHandler
|
||||
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
|
||||
from crewai.agents.cache.cache_handler import CacheHandler
|
||||
from crewai.agents.tools_handler import ToolsHandler
|
||||
from crewai.utilities import I18N, Logger, RPMController
|
||||
|
||||
T = TypeVar("T", bound="BaseAgent")
|
||||
|
||||
@@ -1,65 +1,109 @@
|
||||
import time
|
||||
from typing import TYPE_CHECKING, Optional
|
||||
|
||||
from crewai.memory.entity.entity_memory_item import EntityMemoryItem
|
||||
from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
|
||||
from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
|
||||
from crewai.utilities.converter import ConverterError
|
||||
from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
|
||||
from crewai.utilities import I18N
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from crewai.crew import Crew
|
||||
from crewai.task import Task
|
||||
from crewai.agents.agent_builder.base_agent import BaseAgent
|
||||
|
||||
|
||||
class CrewAgentExecutorMixin:
|
||||
crew: Optional["Crew"]
|
||||
crew_agent: Optional["BaseAgent"]
|
||||
task: Optional["Task"]
|
||||
iterations: int
|
||||
force_answer_max_iterations: int
|
||||
have_forced_answer: bool
|
||||
_i18n: I18N
|
||||
|
||||
def _should_force_answer(self) -> bool:
|
||||
"""Determine if a forced answer is required based on iteration count."""
|
||||
return (
|
||||
self.iterations == self.force_answer_max_iterations
|
||||
) and not self.have_forced_answer
|
||||
|
||||
def _create_short_term_memory(self, output) -> None:
|
||||
"""Create and save a short-term memory item if conditions are met."""
|
||||
if (
|
||||
self.crew
|
||||
and self.crew_agent
|
||||
and self.task
|
||||
and "Action: Delegate work to coworker" not in output.log
|
||||
):
|
||||
try:
|
||||
memory = ShortTermMemoryItem(
|
||||
data=output.log,
|
||||
agent=self.crew_agent.role,
|
||||
metadata={
|
||||
"observation": self.task.description,
|
||||
},
|
||||
)
|
||||
if (
|
||||
hasattr(self.crew, "_short_term_memory")
|
||||
and self.crew._short_term_memory
|
||||
):
|
||||
self.crew._short_term_memory.save(memory)
|
||||
except Exception as e:
|
||||
print(f"Failed to add to short term memory: {e}")
|
||||
pass
|
||||
|
||||
def _create_long_term_memory(self, output) -> None:
|
||||
"""Create and save long-term and entity memory items based on evaluation."""
|
||||
if (
|
||||
self.crew
|
||||
and self.crew.memory
|
||||
and "Action: Delegate work to coworker" not in output.log
|
||||
and self.crew._long_term_memory
|
||||
and self.crew._entity_memory
|
||||
and self.task
|
||||
and self.crew_agent
|
||||
):
|
||||
memory = ShortTermMemoryItem(
|
||||
data=output.log,
|
||||
agent=self.crew_agent.role,
|
||||
metadata={
|
||||
"observation": self.task.description,
|
||||
},
|
||||
)
|
||||
self.crew._short_term_memory.save(memory)
|
||||
try:
|
||||
ltm_agent = TaskEvaluator(self.crew_agent)
|
||||
evaluation = ltm_agent.evaluate(self.task, output.log)
|
||||
|
||||
def _create_long_term_memory(self, output) -> None:
|
||||
if self.crew and self.crew.memory:
|
||||
ltm_agent = TaskEvaluator(self.crew_agent)
|
||||
evaluation = ltm_agent.evaluate(self.task, output.log)
|
||||
if isinstance(evaluation, ConverterError):
|
||||
return
|
||||
|
||||
if isinstance(evaluation, ConverterError):
|
||||
return
|
||||
|
||||
long_term_memory = LongTermMemoryItem(
|
||||
task=self.task.description,
|
||||
agent=self.crew_agent.role,
|
||||
quality=evaluation.quality,
|
||||
datetime=str(time.time()),
|
||||
expected_output=self.task.expected_output,
|
||||
metadata={
|
||||
"suggestions": evaluation.suggestions,
|
||||
"quality": evaluation.quality,
|
||||
},
|
||||
)
|
||||
self.crew._long_term_memory.save(long_term_memory)
|
||||
|
||||
for entity in evaluation.entities:
|
||||
entity_memory = EntityMemoryItem(
|
||||
name=entity.name,
|
||||
type=entity.type,
|
||||
description=entity.description,
|
||||
relationships="\n".join([f"- {r}" for r in entity.relationships]),
|
||||
long_term_memory = LongTermMemoryItem(
|
||||
task=self.task.description,
|
||||
agent=self.crew_agent.role,
|
||||
quality=evaluation.quality,
|
||||
datetime=str(time.time()),
|
||||
expected_output=self.task.expected_output,
|
||||
metadata={
|
||||
"suggestions": evaluation.suggestions,
|
||||
"quality": evaluation.quality,
|
||||
},
|
||||
)
|
||||
self.crew._entity_memory.save(entity_memory)
|
||||
self.crew._long_term_memory.save(long_term_memory)
|
||||
|
||||
for entity in evaluation.entities:
|
||||
entity_memory = EntityMemoryItem(
|
||||
name=entity.name,
|
||||
type=entity.type,
|
||||
description=entity.description,
|
||||
relationships="\n".join(
|
||||
[f"- {r}" for r in entity.relationships]
|
||||
),
|
||||
)
|
||||
self.crew._entity_memory.save(entity_memory)
|
||||
except AttributeError as e:
|
||||
print(f"Missing attributes for long term memory: {e}")
|
||||
pass
|
||||
except Exception as e:
|
||||
print(f"Failed to add to long term memory: {e}")
|
||||
pass
|
||||
|
||||
def _ask_human_input(self, final_answer: dict) -> str:
|
||||
"""Get human input."""
|
||||
"""Prompt human input for final decision making."""
|
||||
return input(
|
||||
self._i18n.slice("getting_input").format(final_answer=final_answer)
|
||||
)
|
||||
|
||||
@@ -1,6 +1,14 @@
|
||||
import threading
|
||||
import time
|
||||
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
|
||||
from typing import (
|
||||
Any,
|
||||
Dict,
|
||||
Iterator,
|
||||
List,
|
||||
Optional,
|
||||
Tuple,
|
||||
Union,
|
||||
)
|
||||
|
||||
from langchain.agents import AgentExecutor
|
||||
from langchain.agents.agent import ExceptionTool
|
||||
@@ -11,13 +19,15 @@ from langchain_core.exceptions import OutputParserException
|
||||
from langchain_core.tools import BaseTool
|
||||
from langchain_core.utils.input import get_color_mapping
|
||||
from pydantic import InstanceOf
|
||||
from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
|
||||
from crewai.agents.agent_builder.base_agent_executor_mixin import (
|
||||
CrewAgentExecutorMixin,
|
||||
)
|
||||
|
||||
from crewai.agents.tools_handler import ToolsHandler
|
||||
from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
|
||||
from crewai.utilities import I18N
|
||||
from crewai.utilities.constants import TRAINING_DATA_FILE
|
||||
from crewai.utilities.training_handler import CrewTrainingHandler
|
||||
from crewai.utilities import I18N
|
||||
|
||||
|
||||
class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
|
||||
@@ -36,6 +36,11 @@ from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
|
||||
from crewai.utilities.formatter import aggregate_raw_outputs_from_task_outputs
|
||||
from crewai.utilities.training_handler import CrewTrainingHandler
|
||||
|
||||
try:
|
||||
import agentops
|
||||
except ImportError:
|
||||
agentops = None
|
||||
|
||||
|
||||
class Crew(BaseModel):
|
||||
"""
|
||||
@@ -56,7 +61,6 @@ class Crew(BaseModel):
|
||||
max_rpm: Maximum number of requests per minute for the crew execution to be respected.
|
||||
prompt_file: Path to the prompt json file to be used for the crew.
|
||||
id: A unique identifier for the crew instance.
|
||||
full_output: Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.
|
||||
task_callback: Callback to be executed after each task for every agents execution.
|
||||
step_callback: Callback to be executed after each step for every agents execution.
|
||||
share_crew: Whether you want to share the complete crew information and execution with crewAI to make the library better, and allow us to train models.
|
||||
@@ -92,10 +96,6 @@ class Crew(BaseModel):
|
||||
default=None,
|
||||
description="Metrics for the LLM usage during all tasks execution.",
|
||||
)
|
||||
full_output: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.",
|
||||
)
|
||||
manager_llm: Optional[Any] = Field(
|
||||
description="Language model that will run the agent.", default=None
|
||||
)
|
||||
@@ -627,13 +627,41 @@ class Crew(BaseModel):
|
||||
return CrewOutput(
|
||||
output=output,
|
||||
tasks_output=[task.output for task in self.tasks if task],
|
||||
token_output=token_usage,
|
||||
token_usage=token_usage,
|
||||
)
|
||||
|
||||
def _finish_execution(self, final_string_output: str) -> None:
|
||||
if self.max_rpm:
|
||||
self._rpm_controller.stop_rpm_counter()
|
||||
if agentops:
|
||||
agentops.end_session(
|
||||
end_state="Success",
|
||||
end_state_reason="Finished Execution",
|
||||
is_auto_end=True,
|
||||
)
|
||||
self._telemetry.end_crew(self, final_string_output)
|
||||
|
||||
def calculate_usage_metrics(self) -> Dict[str, int]:
|
||||
"""Calculates and returns the usage metrics."""
|
||||
total_usage_metrics = {
|
||||
"total_tokens": 0,
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"successful_requests": 0,
|
||||
}
|
||||
|
||||
for agent in self.agents:
|
||||
if hasattr(agent, "_token_process"):
|
||||
token_sum = agent._token_process.get_summary()
|
||||
for key in total_usage_metrics:
|
||||
total_usage_metrics[key] += token_sum.get(key, 0)
|
||||
|
||||
if self.manager_agent and hasattr(self.manager_agent, "_token_process"):
|
||||
token_sum = self.manager_agent._token_process.get_summary()
|
||||
for key in total_usage_metrics:
|
||||
total_usage_metrics[key] += token_sum.get(key, 0)
|
||||
|
||||
return total_usage_metrics
|
||||
|
||||
def __repr__(self):
|
||||
return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from typing import Any, Dict, List, Optional, Union
|
||||
from typing import Any, Dict, List, Union
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
@@ -11,23 +11,34 @@ class CrewOutput(BaseModel):
|
||||
tasks_output: list[TaskOutput] = Field(
|
||||
description="Output of each task", default=[]
|
||||
)
|
||||
token_output: Dict[str, Any] = Field(
|
||||
token_usage: Dict[str, Any] = Field(
|
||||
description="Processed token summary", default={}
|
||||
)
|
||||
|
||||
def result(self) -> Union[str, BaseModel, Dict[str, Any]]:
|
||||
# TODO: Ask @joao what is the desired behavior here
|
||||
def result(
|
||||
self,
|
||||
) -> List[str | BaseModel | Dict[str, Any]]]:
|
||||
"""Return the result of the task based on the available output."""
|
||||
return self.output.result()
|
||||
results = [output.result() for output in self.output]
|
||||
return results
|
||||
|
||||
def raw_output(self) -> str:
|
||||
"""Return the raw output of the task."""
|
||||
return aggregate_raw_outputs_from_task_outputs(self.output)
|
||||
|
||||
def to_output_dict(self) -> Dict[str, Any]:
|
||||
self.output.to_output_dict()
|
||||
def to_output_dict(self) -> List[Dict[str, Any]]:
|
||||
output_dict = [output.to_output_dict() for output in self.output]
|
||||
return output_dict
|
||||
|
||||
def __getitem__(self, key: str) -> Any:
|
||||
self.output[key]
|
||||
if len(self.output) == 0:
|
||||
return None
|
||||
elif len(self.output) == 1:
|
||||
return self.output[0][key]
|
||||
else:
|
||||
return [output[key] for output in self.output]
|
||||
|
||||
# TODO: Confirm with Joao that we want to print the raw output and not the object
|
||||
def __str__(self):
|
||||
return str(self.raw_output())
|
||||
|
||||
@@ -209,8 +209,8 @@ class Task(BaseModel):
|
||||
if self.context:
|
||||
context_list = []
|
||||
for task in self.context:
|
||||
if task.async_execution and task.thread:
|
||||
task.thread.join()
|
||||
if task.async_execution and task._thread:
|
||||
task._thread.join()
|
||||
if task and task.output:
|
||||
context_list.append(task.output.raw_output)
|
||||
context = "\n".join(context_list)
|
||||
|
||||
@@ -52,7 +52,7 @@ class TaskOutput(BaseModel):
|
||||
if self.json_output:
|
||||
output_dict.update(self.json_output)
|
||||
if self.pydantic_output:
|
||||
output_dict.update(self.pydantic_output.dict())
|
||||
output_dict.update(self.pydantic_output.model_dump())
|
||||
return output_dict
|
||||
|
||||
def __str__(self) -> str:
|
||||
|
||||
@@ -11,6 +11,12 @@ from crewai.telemetry import Telemetry
|
||||
from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
|
||||
from crewai.utilities import I18N, Converter, ConverterError, Printer
|
||||
|
||||
agentops = None
|
||||
try:
|
||||
import agentops
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
OPENAI_BIGGER_MODELS = ["gpt-4"]
|
||||
|
||||
|
||||
@@ -91,15 +97,16 @@ class ToolUsage:
|
||||
self.task.increment_tools_errors()
|
||||
self._printer.print(content=f"\n\n{error}\n", color="red")
|
||||
return error
|
||||
return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}" # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}" # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
|
||||
def _use(
|
||||
self,
|
||||
tool_string: str,
|
||||
tool: BaseTool,
|
||||
calling: Union[ToolCalling, InstructorToolCalling],
|
||||
) -> str: # TODO: Fix this return type --> finecwg : I updated return type to str
|
||||
if self._check_tool_repeated_usage(calling=calling): # type: ignore # _check_tool_repeated_usage of "ToolUsage" does not return a value (it only ever returns None)
|
||||
) -> str: # TODO: Fix this return type
|
||||
tool_event = agentops.ToolEvent(name=calling.tool_name) if agentops else None
|
||||
if self._check_tool_repeated_usage(calling=calling): # type: ignore # _check_tool_repeated_usage of "ToolUsage" does not return a value (it only ever returns None)
|
||||
try:
|
||||
result = self._i18n.errors("task_repeated_usage").format(
|
||||
tool_names=self.tools_names
|
||||
@@ -110,13 +117,13 @@ class ToolUsage:
|
||||
tool_name=tool.name,
|
||||
attempts=self._run_attempts,
|
||||
)
|
||||
result = self._format_result(result=result) # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
result = self._format_result(result=result) # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
return result # type: ignore # Fix the reutrn type of this function
|
||||
|
||||
except Exception:
|
||||
self.task.increment_tools_errors()
|
||||
|
||||
result = None # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
|
||||
result = None # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
|
||||
|
||||
if self.tools_handler.cache:
|
||||
result = self.tools_handler.cache.read( # type: ignore # Incompatible types in assignment (expression has type "str | None", variable has type "str")
|
||||
@@ -133,7 +140,7 @@ class ToolUsage:
|
||||
|
||||
if calling.arguments:
|
||||
try:
|
||||
acceptable_args = tool.args_schema.schema()["properties"].keys() # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "schema"
|
||||
acceptable_args = tool.args_schema.schema()["properties"].keys() # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "schema"
|
||||
arguments = {
|
||||
k: v
|
||||
for k, v in calling.arguments.items()
|
||||
@@ -145,7 +152,7 @@ class ToolUsage:
|
||||
arguments = calling.arguments
|
||||
result = tool._run(**arguments)
|
||||
else:
|
||||
arguments = calling.arguments.values() # type: ignore # Incompatible types in assignment (expression has type "dict_values[str, Any]", variable has type "dict[str, Any]")
|
||||
arguments = calling.arguments.values() # type: ignore # Incompatible types in assignment (expression has type "dict_values[str, Any]", variable has type "dict[str, Any]")
|
||||
result = tool._run(*arguments)
|
||||
else:
|
||||
result = tool._run()
|
||||
@@ -164,6 +171,10 @@ class ToolUsage:
|
||||
return error # type: ignore # No return value expected
|
||||
|
||||
self.task.increment_tools_errors()
|
||||
if agentops:
|
||||
agentops.record(
|
||||
agentops.ErrorEvent(exception=e, trigger_event=tool_event)
|
||||
)
|
||||
return self.use(calling=calling, tool_string=tool_string) # type: ignore # No return value expected
|
||||
|
||||
if self.tools_handler:
|
||||
@@ -184,18 +195,20 @@ class ToolUsage:
|
||||
)
|
||||
|
||||
self._printer.print(content=f"\n\n{result}\n", color="purple")
|
||||
if agentops:
|
||||
agentops.record(tool_event)
|
||||
self._telemetry.tool_usage(
|
||||
llm=self.function_calling_llm,
|
||||
tool_name=tool.name,
|
||||
attempts=self._run_attempts,
|
||||
)
|
||||
result = self._format_result(result=result) # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
)
|
||||
result = self._format_result(result=result) # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
return result # type: ignore # No return value expected
|
||||
|
||||
def _format_result(self, result: Any) -> None:
|
||||
self.task.used_tools += 1
|
||||
if self._should_remember_format(): # type: ignore # "_should_remember_format" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
result = self._remember_format(result=result) # type: ignore # "_remember_format" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
result = self._remember_format(result=result) # type: ignore # "_remember_format" of "ToolUsage" does not return a value (it only ever returns None)
|
||||
return result
|
||||
|
||||
def _should_remember_format(self) -> None:
|
||||
|
||||
@@ -5,6 +5,17 @@ from pydantic import BaseModel, Field
|
||||
|
||||
from crewai.utilities import Converter
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
agentops = None
|
||||
try:
|
||||
import agentops
|
||||
from agentops import track_agent
|
||||
except ImportError:
|
||||
|
||||
def track_agent(name):
|
||||
def noop(f):
|
||||
return f
|
||||
|
||||
return noop
|
||||
|
||||
|
||||
class Entity(BaseModel):
|
||||
@@ -38,6 +49,7 @@ class TrainingTaskEvaluation(BaseModel):
|
||||
)
|
||||
|
||||
|
||||
@track_agent(name="Task Evaluator")
|
||||
class TaskEvaluator:
|
||||
def __init__(self, original_agent):
|
||||
self.llm = original_agent.llm
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
from datetime import datetime
|
||||
|
||||
from crewai.utilities.printer import Printer
|
||||
|
||||
from datetime import datetime
|
||||
|
||||
class Logger:
|
||||
_printer = Printer()
|
||||
|
||||
591
tests/cassettes/test_crew_async_kickoff.yaml
Normal file
591
tests/cassettes/test_crew_async_kickoff.yaml
Normal file
@@ -0,0 +1,591 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
|
||||
with dog.\nYour personal goal is: Express hot takes on dog.To give my best complete
|
||||
final answer to the task use the exact following format:\n\nThought: I now can
|
||||
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
|
||||
final answer must be the great and the most complete as possible, it must be
|
||||
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
|
||||
Task: Give me an analysis around dog.\n\nThis is the expect criteria for your
|
||||
final answer: 1 bullet point about dog that''s under 15 words. \n you MUST return
|
||||
the actual complete content as the final answer, not a summary.\n\nBegin! This
|
||||
is VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
|
||||
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, br
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '951'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.34.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.34.0
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: 'data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
I"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
now"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
can"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
give"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
a"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
great"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
Answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
Dogs"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
are"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
incredibly"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
loyal"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
and"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
provide"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
unmatched"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
companionship"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
to"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
humans"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
|
||||
|
||||
|
||||
data: [DONE]
|
||||
|
||||
|
||||
'
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 89d0fa4e7abf53db-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- text/event-stream; charset=utf-8
|
||||
Date:
|
||||
- Tue, 02 Jul 2024 19:17:45 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=6Xl2nvdsXT4uSfQ3C1ZK.LWKGYekVs5ErrLDZOdI.50-1719947865-1.0.1.1-6RQoTCznxe7H868MoxghRegIZaElbG_bN_jbs94hmnsnuR1P9bptoj8o2DbOSvj48ubewyvy8L16mOZHlMLw_A;
|
||||
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=kPTMOkGHQp0ytgVUrm3jFNiB9I.DDI2ONPRTr6IMTeo-1719947865623-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '102'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '16000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9997'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '15999783'
|
||||
x-ratelimit-reset-requests:
|
||||
- 14ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_2c5219e228ce79f0131c497230904013
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages": [{"content": "You are apple Researcher. You have a lot of
|
||||
experience with apple.\nYour personal goal is: Express hot takes on apple.To
|
||||
give my best complete final answer to the task use the exact following format:\n\nThought:
|
||||
I now can give a great answer\nFinal Answer: my best complete final answer to
|
||||
the task.\nYour final answer must be the great and the most complete as possible,
|
||||
it must be outcome described.\n\nI MUST use these formats, my job depends on
|
||||
it!\nCurrent Task: Give me an analysis around apple.\n\nThis is the expect criteria
|
||||
for your final answer: 1 bullet point about apple that''s under 15 words. \n
|
||||
you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
|
||||
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, br
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '961'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.34.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.34.0
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: 'data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
now"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
can"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
give"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
a"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
great"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
Answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
Apple"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
revolution"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"izes"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
technology"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
with"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
sleek"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
designs"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
seamless"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
integration"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
and"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
innovative"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
user"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
|
||||
experiences"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
|
||||
|
||||
|
||||
data: [DONE]
|
||||
|
||||
|
||||
'
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 89d0fa4e7ca907e6-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- text/event-stream; charset=utf-8
|
||||
Date:
|
||||
- Tue, 02 Jul 2024 19:17:45 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=wf2ozMjr46sG0EhuZjpiDNagwTxC05ct3Hn7Y9Rs5AI-1719947865-1.0.1.1-uckxTTr7Yfe6sv4ZznqqrGTEz9E3_Cpp7OAWBIEeNz1Smdjwijw8YV5oYPe_6W4DrEtwVzRDxaqIHlWP55O0QA;
|
||||
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=F9pWw4TeoPa8puOm5RN9Gp2oY0lRoN53ChZ1qFYx1S8-1719947865726-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '168'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '16000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9998'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '15999780'
|
||||
x-ratelimit-reset-requests:
|
||||
- 10ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_e6dfeda5935eae030bcc2da526234635
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages": [{"content": "You are cat Researcher. You have a lot of experience
|
||||
with cat.\nYour personal goal is: Express hot takes on cat.To give my best complete
|
||||
final answer to the task use the exact following format:\n\nThought: I now can
|
||||
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
|
||||
final answer must be the great and the most complete as possible, it must be
|
||||
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
|
||||
Task: Give me an analysis around cat.\n\nThis is the expect criteria for your
|
||||
final answer: 1 bullet point about cat that''s under 15 words. \n you MUST return
|
||||
the actual complete content as the final answer, not a summary.\n\nBegin! This
|
||||
is VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
|
||||
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, br
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '951'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.34.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.34.0
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: 'data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
I"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
now"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
can"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
give"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
a"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
great"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
Answer"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
Cats"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
are"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
master"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ful"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
hunters"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
and"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
brilliant"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
|
||||
problem"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-sol"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"vers"},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
|
||||
|
||||
|
||||
data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
|
||||
|
||||
|
||||
data: [DONE]
|
||||
|
||||
|
||||
'
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 89d0fa4e7ae912d7-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- text/event-stream; charset=utf-8
|
||||
Date:
|
||||
- Tue, 02 Jul 2024 19:17:45 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=y7JNZ8WEp.q5pMXLi79ajfcI.F6MfE0GeYLw34Apkf0-1719947865-1.0.1.1-QKklGeYuOnsQROgqMs42XwqKNvW.mPrmcbtaxMnUg3eSgI7TRnRq4qPuSan0ynDt4Hd9NMuls2FR.Caa1MVr9Q;
|
||||
path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=FVQoSgcvVyiB_o43X6y5MGYgzGojmsQqS.nPObW3JYU-1719947865679-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '132'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '16000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '15999783'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_a06bde4044d3ee75edf08f333139679c
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
File diff suppressed because it is too large
Load Diff
@@ -147,6 +147,7 @@ def test_crew_creation():
|
||||
assert result.raw_output() == expected_string_output
|
||||
assert isinstance(result, CrewOutput)
|
||||
assert len(result.tasks_output) == len(tasks)
|
||||
assert result.result() == [expected_string_output]
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -436,16 +437,18 @@ def test_crew_full_ouput():
|
||||
|
||||
result = crew.kickoff()
|
||||
|
||||
assert result == {
|
||||
"final_output": "Hello!",
|
||||
"tasks_outputs": [task1.output, task2.output],
|
||||
"usage_metrics": {
|
||||
"total_tokens": 517,
|
||||
"prompt_tokens": 466,
|
||||
"completion_tokens": 51,
|
||||
"successful_requests": 3,
|
||||
},
|
||||
expected_usage_metrics = {
|
||||
"total_tokens": 348,
|
||||
"prompt_tokens": 314,
|
||||
"completion_tokens": 34,
|
||||
"successful_requests": 2,
|
||||
}
|
||||
print(result.output)
|
||||
assert result.token_usage == expected_usage_metrics
|
||||
expected_final_string_output = "Hello!"
|
||||
assert result.tasks_output == [task1.output, task2.output]
|
||||
assert result.result() == expected_final_string_output
|
||||
assert result.raw_output() == expected_final_string_output
|
||||
|
||||
|
||||
def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
|
||||
@@ -548,8 +551,9 @@ def test_hierarchical_async_task_execution_completion():
|
||||
)
|
||||
|
||||
hierarchical_result = hierarchical_crew.kickoff()
|
||||
|
||||
assert hierarchical_result.raw_output().startswith(
|
||||
"The history of Artificial Intelligence (AI) is a fascinating journey that charts the evolution of human ingenuity and technological advancement."
|
||||
"The history of artificial intelligence (AI) is a fascinating journey"
|
||||
)
|
||||
|
||||
|
||||
@@ -624,48 +628,9 @@ def test_three_task_with_async_execution():
|
||||
assert result.raw_output().count("\n\n----------\n\n") == 2
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_crew_kickoff_for_each_full_ouput():
|
||||
inputs = [
|
||||
{"topic": "dog"},
|
||||
{"topic": "cat"},
|
||||
{"topic": "apple"},
|
||||
]
|
||||
|
||||
agent = Agent(
|
||||
role="{topic} Researcher",
|
||||
goal="Express hot takes on {topic}.",
|
||||
backstory="You have a lot of experience with {topic}.",
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Give me an analysis around {topic}.",
|
||||
expected_output="1 bullet point about {topic} that's under 15 words.",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[task], full_output=True)
|
||||
results = crew.kickoff_for_each(inputs=inputs)
|
||||
|
||||
assert len(results) == len(inputs)
|
||||
for result in results:
|
||||
assert "usage_metrics" in result
|
||||
assert isinstance(result["usage_metrics"], dict)
|
||||
|
||||
# Assert that all required keys are in usage_metrics and their values are not None
|
||||
for key in [
|
||||
"total_tokens",
|
||||
"prompt_tokens",
|
||||
"completion_tokens",
|
||||
"successful_requests",
|
||||
]:
|
||||
assert key in result["usage_metrics"]
|
||||
assert result["usage_metrics"][key] > 0
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@pytest.mark.asyncio
|
||||
async def test_crew_async_kickoff_for_each_full_ouput():
|
||||
async def test_crew_async_kickoff():
|
||||
inputs = [
|
||||
{"topic": "dog"},
|
||||
{"topic": "cat"},
|
||||
@@ -689,9 +654,6 @@ async def test_crew_async_kickoff_for_each_full_ouput():
|
||||
|
||||
assert len(results) == len(inputs)
|
||||
for result in results:
|
||||
assert "usage_metrics" in result
|
||||
assert isinstance(result["usage_metrics"], dict)
|
||||
|
||||
# Assert that all required keys are in usage_metrics and their values are not None
|
||||
for key in [
|
||||
"total_tokens",
|
||||
@@ -699,9 +661,9 @@ async def test_crew_async_kickoff_for_each_full_ouput():
|
||||
"completion_tokens",
|
||||
"successful_requests",
|
||||
]:
|
||||
assert key in result["usage_metrics"]
|
||||
assert key in result.token_usage
|
||||
# TODO: FIX THIS WHEN USAGE METRICS ARE RE-DONE
|
||||
# assert result["usage_metrics"][key] > 0
|
||||
# assert result.token_usage[key] > 0
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -784,7 +746,9 @@ def test_kickoff_for_each_single_input():
|
||||
results = crew.kickoff_for_each(inputs=inputs)
|
||||
|
||||
assert len(results) == 1
|
||||
assert results == expected_outputs
|
||||
print("RESULT:", results)
|
||||
for result in results:
|
||||
assert result == expected_outputs[0]
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
@@ -1774,3 +1738,8 @@ def test__setup_for_training():
|
||||
|
||||
for agent in agents:
|
||||
assert agent.allow_delegation is False
|
||||
|
||||
|
||||
# TODO: TEST EXPORT OUTPUT TASK WITH PYDANTIC
|
||||
# TODO: TEST EXPORT OUTPUT TASK WITH JSON
|
||||
# TODO: TEST EXPORT OUTPUT TASK CALLBACK
|
||||
|
||||
Reference in New Issue
Block a user