mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-16 03:28:30 +00:00
Merge remote-tracking branch 'refs/remotes/upstream/main'
This commit is contained in:
@@ -55,8 +55,6 @@ class Agent(BaseAgent):
|
||||
tools: Tools at agents disposal
|
||||
step_callback: Callback to be executed after each step of the agent execution.
|
||||
callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
|
||||
allow_code_execution: Enable code execution for the agent.
|
||||
max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
|
||||
"""
|
||||
|
||||
_times_executed: int = PrivateAttr(default=0)
|
||||
@@ -262,6 +260,7 @@ class Agent(BaseAgent):
|
||||
"tools_handler": self.tools_handler,
|
||||
"function_calling_llm": self.function_calling_llm,
|
||||
"callbacks": self.callbacks,
|
||||
"max_tokens": self.max_tokens,
|
||||
}
|
||||
|
||||
if self._rpm_controller:
|
||||
|
||||
@@ -45,6 +45,7 @@ class BaseAgent(ABC, BaseModel):
|
||||
i18n (I18N): Internationalization settings.
|
||||
cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
|
||||
tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
|
||||
max_tokens: Maximum number of tokens for the agent to generate in a response.
|
||||
|
||||
|
||||
Methods:
|
||||
@@ -118,6 +119,9 @@ class BaseAgent(ABC, BaseModel):
|
||||
tools_handler: InstanceOf[ToolsHandler] = Field(
|
||||
default=None, description="An instance of the ToolsHandler class."
|
||||
)
|
||||
max_tokens: Optional[int] = Field(
|
||||
default=None, description="Maximum number of tokens for the agent's execution."
|
||||
)
|
||||
|
||||
_original_role: str | None = None
|
||||
_original_goal: str | None = None
|
||||
@@ -154,7 +158,7 @@ class BaseAgent(ABC, BaseModel):
|
||||
@model_validator(mode="after")
|
||||
def set_private_attrs(self):
|
||||
"""Set private attributes."""
|
||||
self._logger = Logger(self.verbose)
|
||||
self._logger = Logger(verbose=self.verbose)
|
||||
if self.max_rpm and not self._rpm_controller:
|
||||
self._rpm_controller = RPMController(
|
||||
max_rpm=self.max_rpm, logger=self._logger
|
||||
|
||||
@@ -3,7 +3,6 @@ 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
|
||||
@@ -39,18 +38,17 @@ class CrewAgentExecutorMixin:
|
||||
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)
|
||||
self.crew._short_term_memory.save(
|
||||
value=output.log,
|
||||
metadata={
|
||||
"observation": self.task.description,
|
||||
},
|
||||
agent=self.crew_agent.role,
|
||||
)
|
||||
except Exception as e:
|
||||
print(f"Failed to add to short term memory: {e}")
|
||||
pass
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
import threading
|
||||
import time
|
||||
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
|
||||
from typing import Any, Dict, Iterator, List, Literal, Optional, Tuple, Union
|
||||
import click
|
||||
|
||||
|
||||
from langchain.agents import AgentExecutor
|
||||
from langchain.agents.agent import ExceptionTool
|
||||
@@ -11,12 +13,21 @@ from langchain_core.tools import BaseTool
|
||||
from langchain_core.utils.input import get_color_mapping
|
||||
from pydantic import InstanceOf
|
||||
|
||||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||||
from langchain.chains.summarize import load_summarize_chain
|
||||
|
||||
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.exceptions.context_window_exceeding_exception import (
|
||||
LLMContextLengthExceededException,
|
||||
)
|
||||
from crewai.utilities.training_handler import CrewTrainingHandler
|
||||
from crewai.utilities.logger import Logger
|
||||
|
||||
|
||||
class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
@@ -40,6 +51,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
system_template: Optional[str] = None
|
||||
prompt_template: Optional[str] = None
|
||||
response_template: Optional[str] = None
|
||||
_logger: Logger = Logger()
|
||||
_fit_context_window_strategy: Optional[Literal["summarize"]] = "summarize"
|
||||
|
||||
def _call(
|
||||
self,
|
||||
@@ -131,7 +144,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
|
||||
|
||||
# Call the LLM to see what to do.
|
||||
output = self.agent.plan( # type: ignore # Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
|
||||
output = self.agent.plan(
|
||||
intermediate_steps,
|
||||
callbacks=run_manager.get_child() if run_manager else None,
|
||||
**inputs,
|
||||
@@ -185,6 +198,27 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
yield AgentStep(action=output, observation=observation)
|
||||
return
|
||||
|
||||
except Exception as e:
|
||||
if LLMContextLengthExceededException(str(e))._is_context_limit_error(
|
||||
str(e)
|
||||
):
|
||||
output = self._handle_context_length_error(
|
||||
intermediate_steps, run_manager, inputs
|
||||
)
|
||||
|
||||
if isinstance(output, AgentFinish):
|
||||
yield output
|
||||
elif isinstance(output, list):
|
||||
for step in output:
|
||||
yield step
|
||||
return
|
||||
|
||||
yield AgentStep(
|
||||
action=AgentAction("_Exception", str(e), str(e)),
|
||||
observation=str(e),
|
||||
)
|
||||
return
|
||||
|
||||
# If the tool chosen is the finishing tool, then we end and return.
|
||||
if isinstance(output, AgentFinish):
|
||||
if self.should_ask_for_human_input:
|
||||
@@ -235,6 +269,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
agent=self.crew_agent,
|
||||
action=agent_action,
|
||||
)
|
||||
|
||||
tool_calling = tool_usage.parse(agent_action.log)
|
||||
|
||||
if isinstance(tool_calling, ToolUsageErrorException):
|
||||
@@ -280,3 +315,91 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
|
||||
CrewTrainingHandler(TRAINING_DATA_FILE).append(
|
||||
self.crew._train_iteration, agent_id, training_data
|
||||
)
|
||||
|
||||
def _handle_context_length(
|
||||
self, intermediate_steps: List[Tuple[AgentAction, str]]
|
||||
) -> List[Tuple[AgentAction, str]]:
|
||||
text = intermediate_steps[0][1]
|
||||
original_action = intermediate_steps[0][0]
|
||||
|
||||
text_splitter = RecursiveCharacterTextSplitter(
|
||||
separators=["\n\n", "\n"],
|
||||
chunk_size=8000,
|
||||
chunk_overlap=500,
|
||||
)
|
||||
|
||||
if self._fit_context_window_strategy == "summarize":
|
||||
docs = text_splitter.create_documents([text])
|
||||
self._logger.log(
|
||||
"debug",
|
||||
"Summarizing Content, it is recommended to use a RAG tool",
|
||||
color="bold_blue",
|
||||
)
|
||||
summarize_chain = load_summarize_chain(
|
||||
self.llm, chain_type="map_reduce", verbose=True
|
||||
)
|
||||
summarized_docs = []
|
||||
for doc in docs:
|
||||
summary = summarize_chain.invoke(
|
||||
{"input_documents": [doc]}, return_only_outputs=True
|
||||
)
|
||||
|
||||
summarized_docs.append(summary["output_text"])
|
||||
|
||||
formatted_results = "\n\n".join(summarized_docs)
|
||||
summary_step = AgentStep(
|
||||
action=AgentAction(
|
||||
tool=original_action.tool,
|
||||
tool_input=original_action.tool_input,
|
||||
log=original_action.log,
|
||||
),
|
||||
observation=formatted_results,
|
||||
)
|
||||
summary_tuple = (summary_step.action, summary_step.observation)
|
||||
return [summary_tuple]
|
||||
|
||||
return intermediate_steps
|
||||
|
||||
def _handle_context_length_error(
|
||||
self,
|
||||
intermediate_steps: List[Tuple[AgentAction, str]],
|
||||
run_manager: Optional[CallbackManagerForChainRun],
|
||||
inputs: Dict[str, str],
|
||||
) -> Union[AgentFinish, List[AgentStep]]:
|
||||
self._logger.log(
|
||||
"debug",
|
||||
"Context length exceeded. Asking user if they want to use summarize prompt to fit, this will reduce context length.",
|
||||
color="yellow",
|
||||
)
|
||||
user_choice = click.confirm(
|
||||
"Context length exceeded. Do you want to summarize the text to fit models context window?"
|
||||
)
|
||||
if user_choice:
|
||||
self._logger.log(
|
||||
"debug",
|
||||
"Context length exceeded. Using summarize prompt to fit, this will reduce context length.",
|
||||
color="bold_blue",
|
||||
)
|
||||
intermediate_steps = self._handle_context_length(intermediate_steps)
|
||||
|
||||
output = self.agent.plan(
|
||||
intermediate_steps,
|
||||
callbacks=run_manager.get_child() if run_manager else None,
|
||||
**inputs,
|
||||
)
|
||||
|
||||
if isinstance(output, AgentFinish):
|
||||
return output
|
||||
elif isinstance(output, AgentAction):
|
||||
return [AgentStep(action=output, observation=None)]
|
||||
else:
|
||||
return [AgentStep(action=action, observation=None) for action in output]
|
||||
else:
|
||||
self._logger.log(
|
||||
"debug",
|
||||
"Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
|
||||
color="red",
|
||||
)
|
||||
raise SystemExit(
|
||||
"Context length exceeded and user opted not to summarize. Consider using smaller text or RAG tools from crewai_tools."
|
||||
)
|
||||
|
||||
@@ -6,9 +6,10 @@ from crewai.memory.storage.kickoff_task_outputs_storage import (
|
||||
)
|
||||
|
||||
from .create_crew import create_crew
|
||||
from .evaluate_crew import evaluate_crew
|
||||
from .replay_from_task import replay_task_command
|
||||
from .reset_memories_command import reset_memories_command
|
||||
from .test_crew import test_crew
|
||||
from .run_crew import run_crew
|
||||
from .train_crew import train_crew
|
||||
|
||||
|
||||
@@ -144,7 +145,14 @@ def reset_memories(long, short, entities, kickoff_outputs, all):
|
||||
def test(n_iterations: int, model: str):
|
||||
"""Test the crew and evaluate the results."""
|
||||
click.echo(f"Testing the crew for {n_iterations} iterations with model {model}")
|
||||
test_crew(n_iterations, model)
|
||||
evaluate_crew(n_iterations, model)
|
||||
|
||||
|
||||
@crewai.command()
|
||||
def run():
|
||||
"""Run the crew."""
|
||||
click.echo("Running the crew")
|
||||
run_crew()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -3,9 +3,9 @@ import subprocess
|
||||
import click
|
||||
|
||||
|
||||
def test_crew(n_iterations: int, model: str) -> None:
|
||||
def evaluate_crew(n_iterations: int, model: str) -> None:
|
||||
"""
|
||||
Test the crew by running a command in the Poetry environment.
|
||||
Test and Evaluate the crew by running a command in the Poetry environment.
|
||||
|
||||
Args:
|
||||
n_iterations (int): The number of iterations to test the crew.
|
||||
@@ -9,10 +9,14 @@ from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandle
|
||||
|
||||
def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
|
||||
"""
|
||||
Replay the crew execution from a specific task.
|
||||
Reset the crew memories.
|
||||
|
||||
Args:
|
||||
task_id (str): The ID of the task to replay from.
|
||||
long (bool): Whether to reset the long-term memory.
|
||||
short (bool): Whether to reset the short-term memory.
|
||||
entity (bool): Whether to reset the entity memory.
|
||||
kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
|
||||
all (bool): Whether to reset all memories.
|
||||
"""
|
||||
|
||||
try:
|
||||
|
||||
23
src/crewai/cli/run_crew.py
Normal file
23
src/crewai/cli/run_crew.py
Normal file
@@ -0,0 +1,23 @@
|
||||
import subprocess
|
||||
|
||||
import click
|
||||
|
||||
|
||||
def run_crew() -> None:
|
||||
"""
|
||||
Run the crew by running a command in the Poetry environment.
|
||||
"""
|
||||
command = ["poetry", "run", "run_crew"]
|
||||
|
||||
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 running the crew: {e}", err=True)
|
||||
click.echo(e.output, err=True)
|
||||
|
||||
except Exception as e:
|
||||
click.echo(f"An unexpected error occurred: {e}", err=True)
|
||||
@@ -34,6 +34,10 @@ poetry install
|
||||
|
||||
To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:
|
||||
|
||||
```bash
|
||||
$ crewai run
|
||||
```
|
||||
or
|
||||
```bash
|
||||
poetry run {{folder_name}}
|
||||
```
|
||||
|
||||
@@ -48,6 +48,6 @@ class {{crew_name}}Crew():
|
||||
agents=self.agents, # Automatically created by the @agent decorator
|
||||
tasks=self.tasks, # Automatically created by the @task decorator
|
||||
process=Process.sequential,
|
||||
verbose=2,
|
||||
verbose=True,
|
||||
# process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
|
||||
)
|
||||
@@ -48,7 +48,7 @@ def test():
|
||||
"topic": "AI LLMs"
|
||||
}
|
||||
try:
|
||||
{{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), model=sys.argv[2], inputs=inputs)
|
||||
{{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"An error occurred while replaying the crew: {e}")
|
||||
|
||||
@@ -6,10 +6,11 @@ authors = ["Your Name <you@example.com>"]
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = ">=3.10,<=3.13"
|
||||
crewai = { extras = ["tools"], version = "^0.41.1" }
|
||||
crewai = { extras = ["tools"], version = "^0.46.0" }
|
||||
|
||||
[tool.poetry.scripts]
|
||||
{{folder_name}} = "{{folder_name}}.main:run"
|
||||
run_crew = "{{folder_name}}.main:run"
|
||||
train = "{{folder_name}}.main:train"
|
||||
replay = "{{folder_name}}.main:replay"
|
||||
test = "{{folder_name}}.main:test"
|
||||
|
||||
@@ -37,6 +37,7 @@ from crewai.utilities.constants import (
|
||||
TRAINED_AGENTS_DATA_FILE,
|
||||
TRAINING_DATA_FILE,
|
||||
)
|
||||
from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
|
||||
from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
|
||||
from crewai.utilities.formatter import (
|
||||
aggregate_raw_outputs_from_task_outputs,
|
||||
@@ -101,7 +102,7 @@ class Crew(BaseModel):
|
||||
tasks: List[Task] = Field(default_factory=list)
|
||||
agents: List[BaseAgent] = Field(default_factory=list)
|
||||
process: Process = Field(default=Process.sequential)
|
||||
verbose: Union[int, bool] = Field(default=0)
|
||||
verbose: bool = Field(default=False)
|
||||
memory: bool = Field(
|
||||
default=False,
|
||||
description="Whether the crew should use memory to store memories of it's execution",
|
||||
@@ -154,6 +155,10 @@ class Crew(BaseModel):
|
||||
default=False,
|
||||
description="Plan the crew execution and add the plan to the crew.",
|
||||
)
|
||||
planning_llm: Optional[Any] = Field(
|
||||
default=None,
|
||||
description="Language model that will run the AgentPlanner if planning is True.",
|
||||
)
|
||||
task_execution_output_json_files: Optional[List[str]] = Field(
|
||||
default=None,
|
||||
description="List of file paths for task execution JSON files.",
|
||||
@@ -191,7 +196,7 @@ class Crew(BaseModel):
|
||||
def set_private_attrs(self) -> "Crew":
|
||||
"""Set private attributes."""
|
||||
self._cache_handler = CacheHandler()
|
||||
self._logger = Logger(self.verbose)
|
||||
self._logger = Logger(verbose=self.verbose)
|
||||
if self.output_log_file:
|
||||
self._file_handler = FileHandler(self.output_log_file)
|
||||
self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
|
||||
@@ -266,20 +271,6 @@ class Crew(BaseModel):
|
||||
|
||||
return self
|
||||
|
||||
@model_validator(mode="after")
|
||||
def check_tasks_in_hierarchical_process_not_async(self):
|
||||
"""Validates that the tasks in hierarchical process are not flagged with async_execution."""
|
||||
if self.process == Process.hierarchical:
|
||||
for task in self.tasks:
|
||||
if task.async_execution:
|
||||
raise PydanticCustomError(
|
||||
"async_execution_in_hierarchical_process",
|
||||
"Hierarchical process error: Tasks cannot be flagged with async_execution.",
|
||||
{},
|
||||
)
|
||||
|
||||
return self
|
||||
|
||||
@model_validator(mode="after")
|
||||
def validate_end_with_at_most_one_async_task(self):
|
||||
"""Validates that the crew ends with at most one asynchronous task."""
|
||||
@@ -559,15 +550,12 @@ class Crew(BaseModel):
|
||||
def _handle_crew_planning(self):
|
||||
"""Handles the Crew planning."""
|
||||
self._logger.log("info", "Planning the crew execution")
|
||||
result = CrewPlanner(self.tasks)._handle_crew_planning()
|
||||
result = CrewPlanner(
|
||||
tasks=self.tasks, planning_agent_llm=self.planning_llm
|
||||
)._handle_crew_planning()
|
||||
|
||||
if result is not None and hasattr(result, "list_of_plans_per_task"):
|
||||
for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
|
||||
task.description += step_plan
|
||||
else:
|
||||
self._logger.log(
|
||||
"info", "Something went wrong with the planning process of the Crew"
|
||||
)
|
||||
for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
|
||||
task.description += step_plan
|
||||
|
||||
def _store_execution_log(
|
||||
self,
|
||||
@@ -605,7 +593,7 @@ class Crew(BaseModel):
|
||||
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)
|
||||
return self._execute_tasks(self.tasks)
|
||||
|
||||
def _create_manager_agent(self):
|
||||
i18n = I18N(prompt_file=self.prompt_file)
|
||||
@@ -629,7 +617,6 @@ class Crew(BaseModel):
|
||||
def _execute_tasks(
|
||||
self,
|
||||
tasks: List[Task],
|
||||
manager: Optional[BaseAgent] = None,
|
||||
start_index: Optional[int] = 0,
|
||||
was_replayed: bool = False,
|
||||
) -> CrewOutput:
|
||||
@@ -657,13 +644,13 @@ class Crew(BaseModel):
|
||||
last_sync_output = task.output
|
||||
continue
|
||||
|
||||
agent_to_use = self._get_agent_to_use(task, manager)
|
||||
agent_to_use = self._get_agent_to_use(task)
|
||||
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._prepare_agent_tools(task, manager)
|
||||
self._prepare_agent_tools(task)
|
||||
self._log_task_start(task, agent_to_use.role)
|
||||
|
||||
if isinstance(task, ConditionalTask):
|
||||
@@ -729,20 +716,18 @@ class Crew(BaseModel):
|
||||
return skipped_task_output
|
||||
return None
|
||||
|
||||
def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
|
||||
def _prepare_agent_tools(self, task: Task):
|
||||
if self.process == Process.hierarchical:
|
||||
if manager:
|
||||
self._update_manager_tools(task, manager)
|
||||
if self.manager_agent:
|
||||
self._update_manager_tools(task)
|
||||
else:
|
||||
raise ValueError("Manager agent is required for hierarchical process.")
|
||||
elif task.agent and task.agent.allow_delegation:
|
||||
self._add_delegation_tools(task)
|
||||
|
||||
def _get_agent_to_use(
|
||||
self, task: Task, manager: Optional[BaseAgent]
|
||||
) -> Optional[BaseAgent]:
|
||||
def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
|
||||
if self.process == Process.hierarchical:
|
||||
return manager
|
||||
return self.manager_agent
|
||||
return task.agent
|
||||
|
||||
def _add_delegation_tools(self, task: Task):
|
||||
@@ -778,11 +763,14 @@ class Crew(BaseModel):
|
||||
if self.output_log_file:
|
||||
self._file_handler.log(agent=role, task=task.description, status="started")
|
||||
|
||||
def _update_manager_tools(self, task: Task, manager: BaseAgent):
|
||||
if task.agent:
|
||||
manager.tools = task.agent.get_delegation_tools([task.agent])
|
||||
else:
|
||||
manager.tools = manager.get_delegation_tools(self.agents)
|
||||
def _update_manager_tools(self, task: Task):
|
||||
if self.manager_agent:
|
||||
if task.agent:
|
||||
self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
|
||||
else:
|
||||
self.manager_agent.tools = self.manager_agent.get_delegation_tools(
|
||||
self.agents
|
||||
)
|
||||
|
||||
def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
|
||||
context = (
|
||||
@@ -881,7 +869,7 @@ class Crew(BaseModel):
|
||||
self.tasks[i].output = task_output
|
||||
|
||||
self._logging_color = "bold_blue"
|
||||
result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
|
||||
result = self._execute_tasks(self.tasks, start_index, True)
|
||||
return result
|
||||
|
||||
def copy(self):
|
||||
@@ -967,10 +955,19 @@ class Crew(BaseModel):
|
||||
return total_usage_metrics
|
||||
|
||||
def test(
|
||||
self, n_iterations: int, model: str, inputs: Optional[Dict[str, Any]] = None
|
||||
self,
|
||||
n_iterations: int,
|
||||
openai_model_name: str,
|
||||
inputs: Optional[Dict[str, Any]] = None,
|
||||
) -> None:
|
||||
"""Test the crew with the given inputs."""
|
||||
pass
|
||||
"""Test and evaluate the Crew with the given inputs for n iterations."""
|
||||
evaluator = CrewEvaluator(self, openai_model_name)
|
||||
|
||||
for i in range(1, n_iterations + 1):
|
||||
evaluator.set_iteration(i)
|
||||
self.kickoff(inputs=inputs)
|
||||
|
||||
evaluator.print_crew_evaluation_result()
|
||||
|
||||
def __repr__(self):
|
||||
return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
from typing import Any, Dict, Optional
|
||||
from crewai.memory.memory import Memory
|
||||
from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
|
||||
from crewai.memory.storage.rag_storage import RAGStorage
|
||||
@@ -18,8 +19,15 @@ class ShortTermMemory(Memory):
|
||||
)
|
||||
super().__init__(storage)
|
||||
|
||||
def save(self, item: ShortTermMemoryItem) -> None:
|
||||
super().save(item.data, item.metadata, item.agent)
|
||||
def save(
|
||||
self,
|
||||
value: Any,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
agent: Optional[str] = None,
|
||||
) -> None:
|
||||
item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
|
||||
|
||||
super().save(value=item.data, metadata=item.metadata, agent=item.agent)
|
||||
|
||||
def search(self, query: str, score_threshold: float = 0.35):
|
||||
return self.storage.search(query=query, score_threshold=score_threshold) # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
|
||||
|
||||
@@ -3,7 +3,10 @@ from typing import Any, Dict, Optional
|
||||
|
||||
class ShortTermMemoryItem:
|
||||
def __init__(
|
||||
self, data: Any, agent: str, metadata: Optional[Dict[str, Any]] = None
|
||||
self,
|
||||
data: Any,
|
||||
agent: Optional[str] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
):
|
||||
self.data = data
|
||||
self.agent = agent
|
||||
|
||||
@@ -4,7 +4,7 @@ from typing import Any, Dict
|
||||
class Storage:
|
||||
"""Abstract base class defining the storage interface"""
|
||||
|
||||
def save(self, key: str, value: Any, metadata: Dict[str, Any]) -> None:
|
||||
def save(self, value: Any, metadata: Dict[str, Any]) -> None:
|
||||
pass
|
||||
|
||||
def search(self, key: str) -> Dict[str, Any]: # type: ignore
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import datetime
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import threading
|
||||
import uuid
|
||||
from concurrent.futures import Future
|
||||
@@ -8,7 +8,6 @@ from copy import copy
|
||||
from hashlib import md5
|
||||
from typing import Any, Dict, List, Optional, Tuple, Type, Union
|
||||
|
||||
from langchain_openai import ChatOpenAI
|
||||
from opentelemetry.trace import Span
|
||||
from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
|
||||
from pydantic_core import PydanticCustomError
|
||||
@@ -17,10 +16,8 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
|
||||
from crewai.tasks.output_format import OutputFormat
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
from crewai.telemetry.telemetry import Telemetry
|
||||
from crewai.utilities.converter import Converter, ConverterError
|
||||
from crewai.utilities.converter import Converter, convert_to_model
|
||||
from crewai.utilities.i18n import I18N
|
||||
from crewai.utilities.printer import Printer
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
|
||||
|
||||
class Task(BaseModel):
|
||||
@@ -111,6 +108,7 @@ class Task(BaseModel):
|
||||
_original_description: str | None = None
|
||||
_original_expected_output: str | None = None
|
||||
_thread: threading.Thread | None = None
|
||||
_execution_time: float | None = None
|
||||
|
||||
def __init__(__pydantic_self__, **data):
|
||||
config = data.pop("config", {})
|
||||
@@ -124,9 +122,15 @@ class Task(BaseModel):
|
||||
"may_not_set_field", "This field is not to be set by the user.", {}
|
||||
)
|
||||
|
||||
def _set_start_execution_time(self) -> float:
|
||||
return datetime.datetime.now().timestamp()
|
||||
|
||||
def _set_end_execution_time(self, start_time: float) -> None:
|
||||
self._execution_time = datetime.datetime.now().timestamp() - start_time
|
||||
|
||||
@field_validator("output_file")
|
||||
@classmethod
|
||||
def output_file_validattion(cls, value: str) -> str:
|
||||
def output_file_validation(cls, value: str) -> str:
|
||||
"""Validate the output file path by removing the / from the beginning of the path."""
|
||||
if value.startswith("/"):
|
||||
return value[1:]
|
||||
@@ -220,6 +224,7 @@ class Task(BaseModel):
|
||||
f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
|
||||
)
|
||||
|
||||
start_time = self._set_start_execution_time()
|
||||
self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
|
||||
|
||||
self.prompt_context = context
|
||||
@@ -243,6 +248,7 @@ class Task(BaseModel):
|
||||
)
|
||||
self.output = task_output
|
||||
|
||||
self._set_end_execution_time(start_time)
|
||||
if self.callback:
|
||||
self.callback(self.output)
|
||||
|
||||
@@ -326,18 +332,6 @@ class Task(BaseModel):
|
||||
|
||||
return copied_task
|
||||
|
||||
def _create_converter(self, *args, **kwargs) -> Converter:
|
||||
"""Create a converter instance."""
|
||||
if self.agent and not self.converter_cls:
|
||||
converter = self.agent.get_output_converter(*args, **kwargs)
|
||||
elif self.converter_cls:
|
||||
converter = self.converter_cls(*args, **kwargs)
|
||||
|
||||
if not converter:
|
||||
raise Exception("No output converter found or set.")
|
||||
|
||||
return converter
|
||||
|
||||
def _export_output(
|
||||
self, result: str
|
||||
) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
|
||||
@@ -345,75 +339,26 @@ class Task(BaseModel):
|
||||
json_output: Optional[Dict[str, Any]] = None
|
||||
|
||||
if self.output_pydantic or self.output_json:
|
||||
model_output = self._convert_to_model(result)
|
||||
pydantic_output = (
|
||||
model_output if isinstance(model_output, BaseModel) else None
|
||||
model_output = convert_to_model(
|
||||
result,
|
||||
self.output_pydantic,
|
||||
self.output_json,
|
||||
self.agent,
|
||||
self.converter_cls,
|
||||
)
|
||||
if isinstance(model_output, str):
|
||||
|
||||
if isinstance(model_output, BaseModel):
|
||||
pydantic_output = model_output
|
||||
elif isinstance(model_output, dict):
|
||||
json_output = model_output
|
||||
elif isinstance(model_output, str):
|
||||
try:
|
||||
json_output = json.loads(model_output)
|
||||
except json.JSONDecodeError:
|
||||
json_output = None
|
||||
else:
|
||||
json_output = model_output if isinstance(model_output, dict) else None
|
||||
|
||||
return pydantic_output, json_output
|
||||
|
||||
def _convert_to_model(self, result: str) -> Union[dict, BaseModel, str]:
|
||||
model = self.output_pydantic or self.output_json
|
||||
if model is None:
|
||||
return result
|
||||
|
||||
try:
|
||||
return self._validate_model(result, model)
|
||||
except Exception:
|
||||
return self._handle_partial_json(result, model)
|
||||
|
||||
def _validate_model(
|
||||
self, result: str, model: Type[BaseModel]
|
||||
) -> Union[dict, BaseModel]:
|
||||
exported_result = model.model_validate_json(result)
|
||||
if self.output_json:
|
||||
return exported_result.model_dump()
|
||||
return exported_result
|
||||
|
||||
def _handle_partial_json(
|
||||
self, result: str, model: Type[BaseModel]
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
match = re.search(r"({.*})", result, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
exported_result = model.model_validate_json(match.group(0))
|
||||
if self.output_json:
|
||||
return exported_result.model_dump()
|
||||
return exported_result
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return self._convert_with_instructions(result, model)
|
||||
|
||||
def _convert_with_instructions(
|
||||
self, result: str, model: Type[BaseModel]
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
llm = self.agent.function_calling_llm or self.agent.llm # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
|
||||
instructions = self._get_conversion_instructions(model, llm)
|
||||
|
||||
converter = self._create_converter(
|
||||
llm=llm, text=result, model=model, instructions=instructions
|
||||
)
|
||||
exported_result = (
|
||||
converter.to_pydantic() if self.output_pydantic else converter.to_json()
|
||||
)
|
||||
|
||||
if isinstance(exported_result, ConverterError):
|
||||
Printer().print(
|
||||
content=f"{exported_result.message} Using raw output instead.",
|
||||
color="red",
|
||||
)
|
||||
return result
|
||||
|
||||
return exported_result
|
||||
|
||||
def _get_output_format(self) -> OutputFormat:
|
||||
if self.output_json:
|
||||
return OutputFormat.JSON
|
||||
@@ -421,34 +366,22 @@ class Task(BaseModel):
|
||||
return OutputFormat.PYDANTIC
|
||||
return OutputFormat.RAW
|
||||
|
||||
def _get_conversion_instructions(self, model: Type[BaseModel], llm: Any) -> str:
|
||||
instructions = "I'm gonna convert this raw text into valid JSON."
|
||||
if not self._is_gpt(llm):
|
||||
model_schema = PydanticSchemaParser(model=model).get_schema()
|
||||
instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
|
||||
return instructions
|
||||
|
||||
def _save_output(self, content: str) -> None:
|
||||
if not self.output_file:
|
||||
raise Exception("Output file path is not set.")
|
||||
|
||||
directory = os.path.dirname(self.output_file)
|
||||
if directory and not os.path.exists(directory):
|
||||
os.makedirs(directory)
|
||||
with open(self.output_file, "w", encoding="utf-8") as file:
|
||||
file.write(content)
|
||||
|
||||
def _is_gpt(self, llm) -> bool:
|
||||
return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
|
||||
|
||||
def _save_file(self, result: Any) -> None:
|
||||
if self.output_file is None:
|
||||
raise ValueError("output_file is not set.")
|
||||
|
||||
directory = os.path.dirname(self.output_file) # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
|
||||
|
||||
if directory and not os.path.exists(directory):
|
||||
os.makedirs(directory)
|
||||
|
||||
with open(self.output_file, "w", encoding="utf-8") as file: # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
|
||||
file.write(result)
|
||||
with open(self.output_file, "w", encoding="utf-8") as file:
|
||||
if isinstance(result, dict):
|
||||
import json
|
||||
|
||||
json.dump(result, file, ensure_ascii=False, indent=2)
|
||||
else:
|
||||
file.write(str(result))
|
||||
return None
|
||||
|
||||
def __repr__(self):
|
||||
|
||||
@@ -40,7 +40,7 @@ class Telemetry:
|
||||
- Roles of agents in a crew
|
||||
- Tools names available
|
||||
|
||||
Users can opt-in to sharing more complete data suing the `share_crew`
|
||||
Users can opt-in to sharing more complete data using the `share_crew`
|
||||
attribute in the Crew class.
|
||||
"""
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ try:
|
||||
except ImportError:
|
||||
agentops = None
|
||||
|
||||
OPENAI_BIGGER_MODELS = ["gpt-4"]
|
||||
OPENAI_BIGGER_MODELS = ["gpt-4o"]
|
||||
|
||||
|
||||
class ToolUsageErrorException(Exception):
|
||||
@@ -86,7 +86,8 @@ class ToolUsage:
|
||||
) -> str:
|
||||
if isinstance(calling, ToolUsageErrorException):
|
||||
error = calling.message
|
||||
self._printer.print(content=f"\n\n{error}\n", color="red")
|
||||
if self.agent.verbose:
|
||||
self._printer.print(content=f"\n\n{error}\n", color="red")
|
||||
self.task.increment_tools_errors()
|
||||
return error
|
||||
|
||||
@@ -96,7 +97,8 @@ class ToolUsage:
|
||||
except Exception as e:
|
||||
error = getattr(e, "message", str(e))
|
||||
self.task.increment_tools_errors()
|
||||
self._printer.print(content=f"\n\n{error}\n", color="red")
|
||||
if self.agent.verbose:
|
||||
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)
|
||||
|
||||
@@ -112,7 +114,8 @@ class ToolUsage:
|
||||
result = self._i18n.errors("task_repeated_usage").format(
|
||||
tool_names=self.tools_names
|
||||
)
|
||||
self._printer.print(content=f"\n\n{result}\n", color="purple")
|
||||
if self.agent.verbose:
|
||||
self._printer.print(content=f"\n\n{result}\n", color="purple")
|
||||
self._telemetry.tool_repeated_usage(
|
||||
llm=self.function_calling_llm,
|
||||
tool_name=tool.name,
|
||||
@@ -168,7 +171,10 @@ class ToolUsage:
|
||||
f'\n{error_message}.\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
|
||||
).message
|
||||
self.task.increment_tools_errors()
|
||||
self._printer.print(content=f"\n\n{error_message}\n", color="red")
|
||||
if self.agent.verbose:
|
||||
self._printer.print(
|
||||
content=f"\n\n{error_message}\n", color="red"
|
||||
)
|
||||
return error # type: ignore # No return value expected
|
||||
|
||||
self.task.increment_tools_errors()
|
||||
@@ -192,7 +198,8 @@ class ToolUsage:
|
||||
calling=calling, output=result, should_cache=should_cache
|
||||
)
|
||||
|
||||
self._printer.print(content=f"\n\n{result}\n", color="purple")
|
||||
if self.agent.verbose:
|
||||
self._printer.print(content=f"\n\n{result}\n", color="purple")
|
||||
if agentops:
|
||||
agentops.record(tool_event)
|
||||
self._telemetry.tool_usage(
|
||||
@@ -346,7 +353,8 @@ class ToolUsage:
|
||||
if self._run_attempts > self._max_parsing_attempts:
|
||||
self._telemetry.tool_usage_error(llm=self.function_calling_llm)
|
||||
self.task.increment_tools_errors()
|
||||
self._printer.print(content=f"\n\n{e}\n", color="red")
|
||||
if self.agent.verbose:
|
||||
self._printer.print(content=f"\n\n{e}\n", color="red")
|
||||
return ToolUsageErrorException( # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
|
||||
f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
|
||||
)
|
||||
|
||||
@@ -7,6 +7,9 @@ from .parser import YamlParser
|
||||
from .printer import Printer
|
||||
from .prompts import Prompts
|
||||
from .rpm_controller import RPMController
|
||||
from .exceptions.context_window_exceeding_exception import (
|
||||
LLMContextLengthExceededException,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Converter",
|
||||
@@ -19,4 +22,5 @@ __all__ = [
|
||||
"Prompts",
|
||||
"RPMController",
|
||||
"YamlParser",
|
||||
"LLMContextLengthExceededException",
|
||||
]
|
||||
|
||||
@@ -1,9 +1,14 @@
|
||||
import json
|
||||
import re
|
||||
from typing import Any, Optional, Type, Union
|
||||
|
||||
from langchain.schema import HumanMessage, SystemMessage
|
||||
from langchain_openai import ChatOpenAI
|
||||
from pydantic import BaseModel, ValidationError
|
||||
|
||||
from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
|
||||
from crewai.utilities.printer import Printer
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
|
||||
|
||||
class ConverterError(Exception):
|
||||
@@ -72,3 +77,153 @@ class Converter(OutputConverter):
|
||||
def is_gpt(self) -> bool:
|
||||
"""Return if llm provided is of gpt from openai."""
|
||||
return isinstance(self.llm, ChatOpenAI) and self.llm.openai_api_base is None
|
||||
|
||||
|
||||
def convert_to_model(
|
||||
result: str,
|
||||
output_pydantic: Optional[Type[BaseModel]],
|
||||
output_json: Optional[Type[BaseModel]],
|
||||
agent: Any,
|
||||
converter_cls: Optional[Type[Converter]] = None,
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
model = output_pydantic or output_json
|
||||
if model is None:
|
||||
return result
|
||||
|
||||
try:
|
||||
escaped_result = json.dumps(json.loads(result, strict=False))
|
||||
return validate_model(escaped_result, model, bool(output_json))
|
||||
except json.JSONDecodeError as e:
|
||||
Printer().print(
|
||||
content=f"Error parsing JSON: {e}. Attempting to handle partial JSON.",
|
||||
color="yellow",
|
||||
)
|
||||
return handle_partial_json(
|
||||
result, model, bool(output_json), agent, converter_cls
|
||||
)
|
||||
except ValidationError as e:
|
||||
Printer().print(
|
||||
content=f"Pydantic validation error: {e}. Attempting to handle partial JSON.",
|
||||
color="yellow",
|
||||
)
|
||||
return handle_partial_json(
|
||||
result, model, bool(output_json), agent, converter_cls
|
||||
)
|
||||
except Exception as e:
|
||||
Printer().print(
|
||||
content=f"Unexpected error during model conversion: {type(e).__name__}: {e}. Returning original result.",
|
||||
color="red",
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def validate_model(
|
||||
result: str, model: Type[BaseModel], is_json_output: bool
|
||||
) -> Union[dict, BaseModel]:
|
||||
exported_result = model.model_validate_json(result)
|
||||
if is_json_output:
|
||||
return exported_result.model_dump()
|
||||
return exported_result
|
||||
|
||||
|
||||
def handle_partial_json(
|
||||
result: str,
|
||||
model: Type[BaseModel],
|
||||
is_json_output: bool,
|
||||
agent: Any,
|
||||
converter_cls: Optional[Type[Converter]] = None,
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
match = re.search(r"({.*})", result, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
exported_result = model.model_validate_json(match.group(0))
|
||||
if is_json_output:
|
||||
return exported_result.model_dump()
|
||||
return exported_result
|
||||
except json.JSONDecodeError as e:
|
||||
Printer().print(
|
||||
content=f"Error parsing JSON: {e}. The extracted JSON-like string is not valid JSON. Attempting alternative conversion method.",
|
||||
color="yellow",
|
||||
)
|
||||
except ValidationError as e:
|
||||
Printer().print(
|
||||
content=f"Pydantic validation error: {e}. The JSON structure doesn't match the expected model. Attempting alternative conversion method.",
|
||||
color="yellow",
|
||||
)
|
||||
except Exception as e:
|
||||
Printer().print(
|
||||
content=f"Unexpected error during partial JSON handling: {type(e).__name__}: {e}. Attempting alternative conversion method.",
|
||||
color="red",
|
||||
)
|
||||
|
||||
return convert_with_instructions(
|
||||
result, model, is_json_output, agent, converter_cls
|
||||
)
|
||||
|
||||
|
||||
def convert_with_instructions(
|
||||
result: str,
|
||||
model: Type[BaseModel],
|
||||
is_json_output: bool,
|
||||
agent: Any,
|
||||
converter_cls: Optional[Type[Converter]] = None,
|
||||
) -> Union[dict, BaseModel, str]:
|
||||
llm = agent.function_calling_llm or agent.llm
|
||||
instructions = get_conversion_instructions(model, llm)
|
||||
|
||||
converter = create_converter(
|
||||
agent=agent,
|
||||
converter_cls=converter_cls,
|
||||
llm=llm,
|
||||
text=result,
|
||||
model=model,
|
||||
instructions=instructions,
|
||||
)
|
||||
exported_result = (
|
||||
converter.to_pydantic() if not is_json_output else converter.to_json()
|
||||
)
|
||||
|
||||
if isinstance(exported_result, ConverterError):
|
||||
Printer().print(
|
||||
content=f"{exported_result.message} Using raw output instead.",
|
||||
color="red",
|
||||
)
|
||||
return result
|
||||
|
||||
return exported_result
|
||||
|
||||
|
||||
def get_conversion_instructions(model: Type[BaseModel], llm: Any) -> str:
|
||||
instructions = "I'm gonna convert this raw text into valid JSON."
|
||||
if not is_gpt(llm):
|
||||
model_schema = PydanticSchemaParser(model=model).get_schema()
|
||||
instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
|
||||
return instructions
|
||||
|
||||
|
||||
def is_gpt(llm: Any) -> bool:
|
||||
from langchain_openai import ChatOpenAI
|
||||
|
||||
return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
|
||||
|
||||
|
||||
def create_converter(
|
||||
agent: Optional[Any] = None,
|
||||
converter_cls: Optional[Type[Converter]] = None,
|
||||
*args,
|
||||
**kwargs,
|
||||
) -> Converter:
|
||||
if agent and not converter_cls:
|
||||
if hasattr(agent, "get_output_converter"):
|
||||
converter = agent.get_output_converter(*args, **kwargs)
|
||||
else:
|
||||
raise AttributeError("Agent does not have a 'get_output_converter' method")
|
||||
elif converter_cls:
|
||||
converter = converter_cls(*args, **kwargs)
|
||||
else:
|
||||
raise ValueError("Either agent or converter_cls must be provided")
|
||||
|
||||
if not converter:
|
||||
raise Exception("No output converter found or set.")
|
||||
|
||||
return converter
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import json
|
||||
from typing import Any, List, Type, Union
|
||||
from typing import Any, List, Type
|
||||
|
||||
import regex
|
||||
from langchain.output_parsers import PydanticOutputParser
|
||||
@@ -7,29 +7,24 @@ from langchain_core.exceptions import OutputParserException
|
||||
from langchain_core.outputs import Generation
|
||||
from langchain_core.pydantic_v1 import ValidationError
|
||||
from pydantic import BaseModel
|
||||
from pydantic.v1 import BaseModel as V1BaseModel
|
||||
|
||||
|
||||
class CrewPydanticOutputParser(PydanticOutputParser):
|
||||
"""Parses the text into pydantic models"""
|
||||
|
||||
pydantic_object: Union[Type[BaseModel], Type[V1BaseModel]]
|
||||
pydantic_object: Type[BaseModel]
|
||||
|
||||
def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
|
||||
def parse_result(self, result: List[Generation]) -> Any:
|
||||
result[0].text = self._transform_in_valid_json(result[0].text)
|
||||
|
||||
# Treating edge case of function calling llm returning the name instead of tool_name
|
||||
json_object = json.loads(result[0].text)
|
||||
json_object["tool_name"] = (
|
||||
json_object["name"]
|
||||
if "tool_name" not in json_object
|
||||
else json_object["tool_name"]
|
||||
)
|
||||
if "tool_name" not in json_object:
|
||||
json_object["tool_name"] = json_object.get("name", "")
|
||||
result[0].text = json.dumps(json_object)
|
||||
|
||||
json_object = super().parse_result(result)
|
||||
try:
|
||||
return self.pydantic_object.parse_obj(json_object)
|
||||
return self.pydantic_object.model_validate(json_object)
|
||||
except ValidationError as e:
|
||||
name = self.pydantic_object.__name__
|
||||
msg = f"Failed to parse {name} from completion {json_object}. Got: {e}"
|
||||
|
||||
163
src/crewai/utilities/evaluators/crew_evaluator_handler.py
Normal file
163
src/crewai/utilities/evaluators/crew_evaluator_handler.py
Normal file
@@ -0,0 +1,163 @@
|
||||
from collections import defaultdict
|
||||
|
||||
from langchain_openai import ChatOpenAI
|
||||
from pydantic import BaseModel, Field
|
||||
from rich.console import Console
|
||||
from rich.table import Table
|
||||
|
||||
from crewai.agent import Agent
|
||||
from crewai.task import Task
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
|
||||
|
||||
class TaskEvaluationPydanticOutput(BaseModel):
|
||||
quality: float = Field(
|
||||
description="A score from 1 to 10 evaluating on completion, quality, and overall performance from the task_description and task_expected_output to the actual Task Output."
|
||||
)
|
||||
|
||||
|
||||
class CrewEvaluator:
|
||||
"""
|
||||
A class to evaluate the performance of the agents in the crew based on the tasks they have performed.
|
||||
|
||||
Attributes:
|
||||
crew (Crew): The crew of agents to evaluate.
|
||||
openai_model_name (str): The model to use for evaluating the performance of the agents (for now ONLY OpenAI accepted).
|
||||
tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
|
||||
iteration (int): The current iteration of the evaluation.
|
||||
"""
|
||||
|
||||
tasks_scores: defaultdict = defaultdict(list)
|
||||
run_execution_times: defaultdict = defaultdict(list)
|
||||
iteration: int = 0
|
||||
|
||||
def __init__(self, crew, openai_model_name: str):
|
||||
self.crew = crew
|
||||
self.openai_model_name = openai_model_name
|
||||
self._setup_for_evaluating()
|
||||
|
||||
def _setup_for_evaluating(self) -> None:
|
||||
"""Sets up the crew for evaluating."""
|
||||
for task in self.crew.tasks:
|
||||
task.callback = self.evaluate
|
||||
|
||||
def _evaluator_agent(self):
|
||||
return Agent(
|
||||
role="Task Execution Evaluator",
|
||||
goal=(
|
||||
"Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
|
||||
),
|
||||
backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
|
||||
verbose=False,
|
||||
llm=ChatOpenAI(model=self.openai_model_name),
|
||||
)
|
||||
|
||||
def _evaluation_task(
|
||||
self, evaluator_agent: Agent, task_to_evaluate: Task, task_output: str
|
||||
) -> Task:
|
||||
return Task(
|
||||
description=(
|
||||
"Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
|
||||
f"task_description: {task_to_evaluate.description} "
|
||||
f"task_expected_output: {task_to_evaluate.expected_output} "
|
||||
f"agent: {task_to_evaluate.agent.role if task_to_evaluate.agent else None} "
|
||||
f"agent_goal: {task_to_evaluate.agent.goal if task_to_evaluate.agent else None} "
|
||||
f"Task Output: {task_output}"
|
||||
),
|
||||
expected_output="Evaluation Score from 1 to 10 based on the performance of the agents on the tasks",
|
||||
agent=evaluator_agent,
|
||||
output_pydantic=TaskEvaluationPydanticOutput,
|
||||
)
|
||||
|
||||
def set_iteration(self, iteration: int) -> None:
|
||||
self.iteration = iteration
|
||||
|
||||
def print_crew_evaluation_result(self) -> None:
|
||||
"""
|
||||
Prints the evaluation result of the crew in a table.
|
||||
A Crew with 2 tasks using the command crewai test -n 2
|
||||
will output the following table:
|
||||
|
||||
Task Scores
|
||||
(1-10 Higher is better)
|
||||
┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
|
||||
┃ Tasks/Crew ┃ Run 1 ┃ Run 2 ┃ Avg. Total ┃
|
||||
┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
|
||||
│ Task 1 │ 10.0 │ 9.0 │ 9.5 │
|
||||
│ Task 2 │ 9.0 │ 9.0 │ 9.0 │
|
||||
│ Crew │ 9.5 │ 9.0 │ 9.2 │
|
||||
└────────────┴───────┴───────┴────────────┘
|
||||
"""
|
||||
task_averages = [
|
||||
sum(scores) / len(scores) for scores in zip(*self.tasks_scores.values())
|
||||
]
|
||||
crew_average = sum(task_averages) / len(task_averages)
|
||||
|
||||
# Create a table
|
||||
table = Table(title="Tasks Scores \n (1-10 Higher is better)")
|
||||
|
||||
# Add columns for the table
|
||||
table.add_column("Tasks/Crew")
|
||||
for run in range(1, len(self.tasks_scores) + 1):
|
||||
table.add_column(f"Run {run}")
|
||||
table.add_column("Avg. Total")
|
||||
|
||||
# Add rows for each task
|
||||
for task_index in range(len(task_averages)):
|
||||
task_scores = [
|
||||
self.tasks_scores[run][task_index]
|
||||
for run in range(1, len(self.tasks_scores) + 1)
|
||||
]
|
||||
avg_score = task_averages[task_index]
|
||||
table.add_row(
|
||||
f"Task {task_index + 1}", *map(str, task_scores), f"{avg_score:.1f}"
|
||||
)
|
||||
|
||||
# Add a row for the crew average
|
||||
crew_scores = [
|
||||
sum(self.tasks_scores[run]) / len(self.tasks_scores[run])
|
||||
for run in range(1, len(self.tasks_scores) + 1)
|
||||
]
|
||||
table.add_row("Crew", *map(str, crew_scores), f"{crew_average:.1f}")
|
||||
|
||||
run_exec_times = [
|
||||
int(sum(tasks_exec_times))
|
||||
for _, tasks_exec_times in self.run_execution_times.items()
|
||||
]
|
||||
execution_time_avg = int(sum(run_exec_times) / len(run_exec_times))
|
||||
table.add_row(
|
||||
"Execution Time (s)",
|
||||
*map(str, run_exec_times),
|
||||
f"{execution_time_avg}",
|
||||
)
|
||||
# Display the table in the terminal
|
||||
console = Console()
|
||||
console.print(table)
|
||||
|
||||
def evaluate(self, task_output: TaskOutput):
|
||||
"""Evaluates the performance of the agents in the crew based on the tasks they have performed."""
|
||||
current_task = None
|
||||
for task in self.crew.tasks:
|
||||
if task.description == task_output.description:
|
||||
current_task = task
|
||||
break
|
||||
|
||||
if not current_task or not task_output:
|
||||
raise ValueError(
|
||||
"Task to evaluate and task output are required for evaluation"
|
||||
)
|
||||
|
||||
evaluator_agent = self._evaluator_agent()
|
||||
evaluation_task = self._evaluation_task(
|
||||
evaluator_agent, current_task, task_output.raw
|
||||
)
|
||||
|
||||
evaluation_result = evaluation_task.execute_sync()
|
||||
|
||||
if isinstance(evaluation_result.pydantic, TaskEvaluationPydanticOutput):
|
||||
self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
|
||||
self.run_execution_times[self.iteration].append(
|
||||
current_task._execution_time
|
||||
)
|
||||
else:
|
||||
raise ValueError("Evaluation result is not in the expected format")
|
||||
@@ -54,23 +54,23 @@ class TaskEvaluator:
|
||||
def __init__(self, original_agent):
|
||||
self.llm = original_agent.llm
|
||||
|
||||
def evaluate(self, task, ouput) -> TaskEvaluation:
|
||||
def evaluate(self, task, output) -> TaskEvaluation:
|
||||
evaluation_query = (
|
||||
f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
|
||||
f"Task Description:\n{task.description}\n\n"
|
||||
f"Expected Output:\n{task.expected_output}\n\n"
|
||||
f"Actual Output:\n{ouput}\n\n"
|
||||
f"Actual Output:\n{output}\n\n"
|
||||
"Please provide:\n"
|
||||
"- Bullet points suggestions to improve future similar tasks\n"
|
||||
"- A score from 0 to 10 evaluating on completion, quality, and overall performance"
|
||||
"- Entities extracted from the task output, if any, their type, description, and relationships"
|
||||
)
|
||||
|
||||
instructions = "I'm gonna convert this raw text into valid JSON."
|
||||
instructions = "Convert all responses into valid JSON output."
|
||||
|
||||
if not self._is_gpt(self.llm):
|
||||
model_schema = PydanticSchemaParser(model=TaskEvaluation).get_schema()
|
||||
instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
|
||||
instructions = f"{instructions}\n\nReturn only valid JSON with the following schema:\n```json\n{model_schema}\n```"
|
||||
|
||||
converter = Converter(
|
||||
llm=self.llm,
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
class LLMContextLengthExceededException(Exception):
|
||||
CONTEXT_LIMIT_ERRORS = [
|
||||
"maximum context length",
|
||||
"context length exceeded",
|
||||
"context_length_exceeded",
|
||||
"context window full",
|
||||
"too many tokens",
|
||||
"input is too long",
|
||||
"exceeds token limit",
|
||||
]
|
||||
|
||||
def __init__(self, error_message: str):
|
||||
self.original_error_message = error_message
|
||||
super().__init__(self._get_error_message(error_message))
|
||||
|
||||
def _is_context_limit_error(self, error_message: str) -> bool:
|
||||
return any(
|
||||
phrase.lower() in error_message.lower()
|
||||
for phrase in self.CONTEXT_LIMIT_ERRORS
|
||||
)
|
||||
|
||||
def _get_error_message(self, error_message: str):
|
||||
return (
|
||||
f"LLM context length exceeded. Original error: {error_message}\n"
|
||||
"Consider using a smaller input or implementing a text splitting strategy."
|
||||
)
|
||||
@@ -6,15 +6,11 @@ from datetime import datetime
|
||||
class Logger:
|
||||
_printer = Printer()
|
||||
|
||||
def __init__(self, verbose_level=0):
|
||||
verbose_level = (
|
||||
2 if isinstance(verbose_level, bool) and verbose_level else verbose_level
|
||||
)
|
||||
self.verbose_level = verbose_level
|
||||
def __init__(self, verbose=False):
|
||||
self.verbose = verbose
|
||||
|
||||
def log(self, level, message, color="bold_green"):
|
||||
level_map = {"debug": 1, "info": 2}
|
||||
if self.verbose_level and level_map.get(level, 0) <= self.verbose_level:
|
||||
if self.verbose:
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
self._printer.print(
|
||||
f"[{timestamp}][{level.upper()}]: {message}", color=color
|
||||
|
||||
@@ -1,17 +1,28 @@
|
||||
import re
|
||||
|
||||
|
||||
class YamlParser:
|
||||
@staticmethod
|
||||
def parse(file):
|
||||
"""
|
||||
Parses a YAML file, modifies specific patterns, and checks for unsupported 'context' usage.
|
||||
Args:
|
||||
file (file object): The YAML file to parse.
|
||||
Returns:
|
||||
str: The modified content of the YAML file.
|
||||
Raises:
|
||||
ValueError: If 'context:' is used incorrectly.
|
||||
"""
|
||||
content = file.read()
|
||||
|
||||
# Replace single { and } with doubled ones, while leaving already doubled ones intact and the other special characters {# and {%
|
||||
modified_content = re.sub(r"(?<!\{){(?!\{)(?!\#)(?!\%)", "{{", content)
|
||||
modified_content = re.sub(
|
||||
r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content
|
||||
)
|
||||
modified_content = re.sub(r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content)
|
||||
|
||||
# Check for 'context:' not followed by '[' and raise an error
|
||||
if re.search(r"context:(?!\s*\[)", modified_content):
|
||||
raise ValueError(
|
||||
"Context is currently only supported in code when creating a task. Please use the 'context' key in the task configuration."
|
||||
"Context is currently only supported in code when creating a task. "
|
||||
"Please use the 'context' key in the task configuration."
|
||||
)
|
||||
|
||||
return modified_content
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
from typing import List, Optional
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from langchain_openai import ChatOpenAI
|
||||
from pydantic import BaseModel
|
||||
|
||||
from crewai.agent import Agent
|
||||
@@ -11,17 +12,27 @@ class PlannerTaskPydanticOutput(BaseModel):
|
||||
|
||||
|
||||
class CrewPlanner:
|
||||
def __init__(self, tasks: List[Task]):
|
||||
def __init__(self, tasks: List[Task], planning_agent_llm: Optional[Any] = None):
|
||||
self.tasks = tasks
|
||||
|
||||
def _handle_crew_planning(self) -> Optional[BaseModel]:
|
||||
if planning_agent_llm is None:
|
||||
self.planning_agent_llm = ChatOpenAI(model="gpt-4o-mini")
|
||||
else:
|
||||
self.planning_agent_llm = planning_agent_llm
|
||||
|
||||
def _handle_crew_planning(self) -> PlannerTaskPydanticOutput:
|
||||
"""Handles the Crew planning by creating detailed step-by-step plans for each task."""
|
||||
planning_agent = self._create_planning_agent()
|
||||
tasks_summary = self._create_tasks_summary()
|
||||
|
||||
planner_task = self._create_planner_task(planning_agent, tasks_summary)
|
||||
|
||||
return planner_task.execute_sync().pydantic
|
||||
result = planner_task.execute_sync()
|
||||
|
||||
if isinstance(result.pydantic, PlannerTaskPydanticOutput):
|
||||
return result.pydantic
|
||||
|
||||
raise ValueError("Failed to get the Planning output")
|
||||
|
||||
def _create_planning_agent(self) -> Agent:
|
||||
"""Creates the planning agent for the crew planning."""
|
||||
@@ -32,6 +43,7 @@ class CrewPlanner:
|
||||
"available to each agent so that they can perform the tasks in an exemplary manner"
|
||||
),
|
||||
backstory="Planner agent for crew planning",
|
||||
llm=self.planning_agent_llm,
|
||||
)
|
||||
|
||||
def _create_planner_task(self, planning_agent: Agent, tasks_summary: str) -> Task:
|
||||
|
||||
@@ -16,11 +16,13 @@ class PydanticSchemaParser(BaseModel):
|
||||
return self._get_model_schema(self.model)
|
||||
|
||||
def _get_model_schema(self, model, depth=0) -> str:
|
||||
lines = []
|
||||
indent = " " * depth
|
||||
lines = [f"{indent}{{"]
|
||||
for field_name, field in model.model_fields.items():
|
||||
field_type_str = self._get_field_type(field, depth + 1)
|
||||
lines.append(f"{' ' * 4 * depth}- {field_name}: {field_type_str}")
|
||||
|
||||
lines.append(f"{indent} {field_name}: {field_type_str},")
|
||||
lines[-1] = lines[-1].rstrip(",") # Remove trailing comma from last item
|
||||
lines.append(f"{indent}}}")
|
||||
return "\n".join(lines)
|
||||
|
||||
def _get_field_type(self, field, depth) -> str:
|
||||
@@ -35,6 +37,6 @@ class PydanticSchemaParser(BaseModel):
|
||||
else:
|
||||
return f"List[{list_item_type.__name__}]"
|
||||
elif issubclass(field_type, BaseModel):
|
||||
return f"\n{self._get_model_schema(field_type, depth)}"
|
||||
return self._get_model_schema(field_type, depth)
|
||||
else:
|
||||
return field_type.__name__
|
||||
|
||||
@@ -10,24 +10,24 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
|
||||
class TokenCalcHandler(BaseCallbackHandler):
|
||||
model_name: str = ""
|
||||
token_cost_process: TokenProcess
|
||||
encoding: tiktoken.Encoding
|
||||
|
||||
def __init__(self, model_name, token_cost_process):
|
||||
self.model_name = model_name
|
||||
self.token_cost_process = token_cost_process
|
||||
try:
|
||||
self.encoding = tiktoken.encoding_for_model(self.model_name)
|
||||
except KeyError:
|
||||
self.encoding = tiktoken.get_encoding("cl100k_base")
|
||||
|
||||
def on_llm_start(
|
||||
self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
|
||||
) -> None:
|
||||
try:
|
||||
encoding = tiktoken.encoding_for_model(self.model_name)
|
||||
except KeyError:
|
||||
encoding = tiktoken.get_encoding("cl100k_base")
|
||||
|
||||
if self.token_cost_process is None:
|
||||
return
|
||||
|
||||
for prompt in prompts:
|
||||
self.token_cost_process.sum_prompt_tokens(len(encoding.encode(prompt)))
|
||||
self.token_cost_process.sum_prompt_tokens(len(self.encoding.encode(prompt)))
|
||||
|
||||
async def on_llm_new_token(self, token: str, **kwargs) -> None:
|
||||
self.token_cost_process.sum_completion_tokens(1)
|
||||
|
||||
Reference in New Issue
Block a user