mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-09 16:18:30 +00:00
Add support for custom LLM implementations (#2277)
* Add support for custom LLM implementations Co-Authored-By: Joe Moura <joao@crewai.com> * Fix import sorting and type annotations Co-Authored-By: Joe Moura <joao@crewai.com> * Fix linting issues with import sorting Co-Authored-By: Joe Moura <joao@crewai.com> * Fix type errors in crew.py by updating tool-related methods to return List[BaseTool] Co-Authored-By: Joe Moura <joao@crewai.com> * Enhance custom LLM implementation with better error handling, documentation, and test coverage Co-Authored-By: Joe Moura <joao@crewai.com> * Refactor LLM module by extracting BaseLLM to a separate file This commit moves the BaseLLM abstract base class from llm.py to a new file llms/base_llm.py to improve code organization. The changes include: - Creating a new file src/crewai/llms/base_llm.py - Moving the BaseLLM class to the new file - Updating imports in __init__.py and llm.py to reflect the new location - Updating test cases to use the new import path The refactoring maintains the existing functionality while improving the project's module structure. * Add AISuite LLM support and update dependencies - Integrate AISuite as a new third-party LLM option - Update pyproject.toml and uv.lock to include aisuite package - Modify BaseLLM to support more flexible initialization - Remove unnecessary LLM imports across multiple files - Implement AISuiteLLM with basic chat completion functionality * Update AISuiteLLM and LLM utility type handling - Modify AISuiteLLM to support more flexible input types for messages - Update type hints in AISuiteLLM to allow string or list of message dictionaries - Enhance LLM utility function to support broader LLM type annotations - Remove default `self.stop` attribute from BaseLLM initialization * Update LLM imports and type hints across multiple files - Modify imports in crew_chat.py to use LLM instead of BaseLLM - Update type hints in llm_utils.py to use LLM type - Add optional `stop` parameter to BaseLLM initialization - Refactor type handling for LLM creation and usage * Improve stop words handling in CrewAgentExecutor - Add support for handling existing stop words in LLM configuration - Ensure stop words are correctly merged and deduplicated - Update type hints to support both LLM and BaseLLM types * Remove abstract method set_callbacks from BaseLLM class * Enhance CustomLLM and JWTAuthLLM initialization with model parameter - Update CustomLLM to accept a model parameter during initialization - Modify test cases to include the new model argument - Ensure JWTAuthLLM and TimeoutHandlingLLM also utilize the model parameter in their constructors - Update type hints in create_llm function to support both LLM and BaseLLM types * Enhance create_llm function to support BaseLLM type - Update the create_llm function to accept both LLM and BaseLLM instances - Ensure compatibility with existing LLM handling logic * Update type hint for initialize_chat_llm to support BaseLLM - Modify the return type of initialize_chat_llm function to allow for both LLM and BaseLLM instances - Ensure compatibility with recent changes in create_llm function * Refactor AISuiteLLM to include tools parameter in completion methods - Update the _prepare_completion_params method to accept an optional tools parameter - Modify the chat completion method to utilize the new tools parameter for enhanced functionality - Clean up print statements for better code clarity * Remove unused tool_calls handling in AISuiteLLM chat completion method for cleaner code. * Refactor Crew class and LLM hierarchy for improved type handling and code clarity - Update Crew class methods to enhance readability with consistent formatting and type hints. - Change LLM class to inherit from BaseLLM for better structure. - Remove unnecessary type checks and streamline tool handling in CrewAgentExecutor. - Adjust BaseLLM to provide default implementations for stop words and context window size methods. - Clean up AISuiteLLM by removing unused methods related to stop words and context window size. * Remove unused `stream` method from `BaseLLM` class to enhance code clarity and maintainability. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Joe Moura <joao@crewai.com> Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com> Co-authored-by: João Moura <joaomdmoura@gmail.com> Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot]
committed by
GitHub
GitHub
parent
3dea3d0183
commit
807c13e144
@@ -6,8 +6,9 @@ import warnings
|
||||
from concurrent.futures import Future
|
||||
from copy import copy as shallow_copy
|
||||
from hashlib import md5
|
||||
from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
|
||||
from typing import Any, Callable, Dict, List, Optional, Set, Tuple, TypeVar, Union, cast
|
||||
|
||||
from langchain_core.tools import BaseTool as LangchainBaseTool
|
||||
from pydantic import (
|
||||
UUID4,
|
||||
BaseModel,
|
||||
@@ -26,7 +27,7 @@ from crewai.agents.cache import CacheHandler
|
||||
from crewai.crews.crew_output import CrewOutput
|
||||
from crewai.knowledge.knowledge import Knowledge
|
||||
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
|
||||
from crewai.llm import LLM
|
||||
from crewai.llm import LLM, BaseLLM
|
||||
from crewai.memory.entity.entity_memory import EntityMemory
|
||||
from crewai.memory.long_term.long_term_memory import LongTermMemory
|
||||
from crewai.memory.short_term.short_term_memory import ShortTermMemory
|
||||
@@ -37,7 +38,7 @@ from crewai.task import Task
|
||||
from crewai.tasks.conditional_task import ConditionalTask
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
from crewai.tools.agent_tools.agent_tools import AgentTools
|
||||
from crewai.tools.base_tool import Tool
|
||||
from crewai.tools.base_tool import BaseTool, Tool
|
||||
from crewai.types.usage_metrics import UsageMetrics
|
||||
from crewai.utilities import I18N, FileHandler, Logger, RPMController
|
||||
from crewai.utilities.constants import TRAINING_DATA_FILE
|
||||
@@ -153,7 +154,7 @@ class Crew(BaseModel):
|
||||
default=None,
|
||||
description="Metrics for the LLM usage during all tasks execution.",
|
||||
)
|
||||
manager_llm: Optional[Any] = Field(
|
||||
manager_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
|
||||
description="Language model that will run the agent.", default=None
|
||||
)
|
||||
manager_agent: Optional[BaseAgent] = Field(
|
||||
@@ -187,7 +188,7 @@ class Crew(BaseModel):
|
||||
default=None,
|
||||
description="Maximum number of requests per minute for the crew execution to be respected.",
|
||||
)
|
||||
prompt_file: str = Field(
|
||||
prompt_file: Optional[str] = Field(
|
||||
default=None,
|
||||
description="Path to the prompt json file to be used for the crew.",
|
||||
)
|
||||
@@ -199,7 +200,7 @@ class Crew(BaseModel):
|
||||
default=False,
|
||||
description="Plan the crew execution and add the plan to the crew.",
|
||||
)
|
||||
planning_llm: Optional[Any] = Field(
|
||||
planning_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
|
||||
default=None,
|
||||
description="Language model that will run the AgentPlanner if planning is True.",
|
||||
)
|
||||
@@ -215,7 +216,7 @@ class Crew(BaseModel):
|
||||
default=None,
|
||||
description="Knowledge sources for the crew. Add knowledge sources to the knowledge object.",
|
||||
)
|
||||
chat_llm: Optional[Any] = Field(
|
||||
chat_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
|
||||
default=None,
|
||||
description="LLM used to handle chatting with the crew.",
|
||||
)
|
||||
@@ -819,7 +820,12 @@ class Crew(BaseModel):
|
||||
|
||||
# Determine which tools to use - task tools take precedence over agent tools
|
||||
tools_for_task = task.tools or agent_to_use.tools or []
|
||||
tools_for_task = self._prepare_tools(agent_to_use, task, tools_for_task)
|
||||
# Prepare tools and ensure they're compatible with task execution
|
||||
tools_for_task = self._prepare_tools(
|
||||
agent_to_use,
|
||||
task,
|
||||
cast(Union[List[Tool], List[BaseTool]], tools_for_task),
|
||||
)
|
||||
|
||||
self._log_task_start(task, agent_to_use.role)
|
||||
|
||||
@@ -838,7 +844,7 @@ class Crew(BaseModel):
|
||||
future = task.execute_async(
|
||||
agent=agent_to_use,
|
||||
context=context,
|
||||
tools=tools_for_task,
|
||||
tools=cast(List[BaseTool], tools_for_task),
|
||||
)
|
||||
futures.append((task, future, task_index))
|
||||
else:
|
||||
@@ -850,7 +856,7 @@ class Crew(BaseModel):
|
||||
task_output = task.execute_sync(
|
||||
agent=agent_to_use,
|
||||
context=context,
|
||||
tools=tools_for_task,
|
||||
tools=cast(List[BaseTool], tools_for_task),
|
||||
)
|
||||
task_outputs.append(task_output)
|
||||
self._process_task_result(task, task_output)
|
||||
@@ -888,10 +894,12 @@ class Crew(BaseModel):
|
||||
return None
|
||||
|
||||
def _prepare_tools(
|
||||
self, agent: BaseAgent, task: Task, tools: List[Tool]
|
||||
) -> List[Tool]:
|
||||
self, agent: BaseAgent, task: Task, tools: Union[List[Tool], List[BaseTool]]
|
||||
) -> List[BaseTool]:
|
||||
# Add delegation tools if agent allows delegation
|
||||
if agent.allow_delegation:
|
||||
if hasattr(agent, "allow_delegation") and getattr(
|
||||
agent, "allow_delegation", False
|
||||
):
|
||||
if self.process == Process.hierarchical:
|
||||
if self.manager_agent:
|
||||
tools = self._update_manager_tools(task, tools)
|
||||
@@ -900,17 +908,24 @@ class Crew(BaseModel):
|
||||
"Manager agent is required for hierarchical process."
|
||||
)
|
||||
|
||||
elif agent and agent.allow_delegation:
|
||||
elif agent:
|
||||
tools = self._add_delegation_tools(task, tools)
|
||||
|
||||
# Add code execution tools if agent allows code execution
|
||||
if agent.allow_code_execution:
|
||||
if hasattr(agent, "allow_code_execution") and getattr(
|
||||
agent, "allow_code_execution", False
|
||||
):
|
||||
tools = self._add_code_execution_tools(agent, tools)
|
||||
|
||||
if agent and agent.multimodal:
|
||||
if (
|
||||
agent
|
||||
and hasattr(agent, "multimodal")
|
||||
and getattr(agent, "multimodal", False)
|
||||
):
|
||||
tools = self._add_multimodal_tools(agent, tools)
|
||||
|
||||
return tools
|
||||
# Return a List[BaseTool] which is compatible with both Task.execute_sync and Task.execute_async
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
|
||||
if self.process == Process.hierarchical:
|
||||
@@ -918,11 +933,13 @@ class Crew(BaseModel):
|
||||
return task.agent
|
||||
|
||||
def _merge_tools(
|
||||
self, existing_tools: List[Tool], new_tools: List[Tool]
|
||||
) -> List[Tool]:
|
||||
self,
|
||||
existing_tools: Union[List[Tool], List[BaseTool]],
|
||||
new_tools: Union[List[Tool], List[BaseTool]],
|
||||
) -> List[BaseTool]:
|
||||
"""Merge new tools into existing tools list, avoiding duplicates by tool name."""
|
||||
if not new_tools:
|
||||
return existing_tools
|
||||
return cast(List[BaseTool], existing_tools)
|
||||
|
||||
# Create mapping of tool names to new tools
|
||||
new_tool_map = {tool.name: tool for tool in new_tools}
|
||||
@@ -933,23 +950,41 @@ class Crew(BaseModel):
|
||||
# Add all new tools
|
||||
tools.extend(new_tools)
|
||||
|
||||
return tools
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _inject_delegation_tools(
|
||||
self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]
|
||||
):
|
||||
delegation_tools = task_agent.get_delegation_tools(agents)
|
||||
return self._merge_tools(tools, delegation_tools)
|
||||
self,
|
||||
tools: Union[List[Tool], List[BaseTool]],
|
||||
task_agent: BaseAgent,
|
||||
agents: List[BaseAgent],
|
||||
) -> List[BaseTool]:
|
||||
if hasattr(task_agent, "get_delegation_tools"):
|
||||
delegation_tools = task_agent.get_delegation_tools(agents)
|
||||
# Cast delegation_tools to the expected type for _merge_tools
|
||||
return self._merge_tools(tools, cast(List[BaseTool], delegation_tools))
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _add_multimodal_tools(self, agent: BaseAgent, tools: List[Tool]):
|
||||
multimodal_tools = agent.get_multimodal_tools()
|
||||
return self._merge_tools(tools, multimodal_tools)
|
||||
def _add_multimodal_tools(
|
||||
self, agent: BaseAgent, tools: Union[List[Tool], List[BaseTool]]
|
||||
) -> List[BaseTool]:
|
||||
if hasattr(agent, "get_multimodal_tools"):
|
||||
multimodal_tools = agent.get_multimodal_tools()
|
||||
# Cast multimodal_tools to the expected type for _merge_tools
|
||||
return self._merge_tools(tools, cast(List[BaseTool], multimodal_tools))
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _add_code_execution_tools(self, agent: BaseAgent, tools: List[Tool]):
|
||||
code_tools = agent.get_code_execution_tools()
|
||||
return self._merge_tools(tools, code_tools)
|
||||
def _add_code_execution_tools(
|
||||
self, agent: BaseAgent, tools: Union[List[Tool], List[BaseTool]]
|
||||
) -> List[BaseTool]:
|
||||
if hasattr(agent, "get_code_execution_tools"):
|
||||
code_tools = agent.get_code_execution_tools()
|
||||
# Cast code_tools to the expected type for _merge_tools
|
||||
return self._merge_tools(tools, cast(List[BaseTool], code_tools))
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _add_delegation_tools(self, task: Task, tools: List[Tool]):
|
||||
def _add_delegation_tools(
|
||||
self, task: Task, tools: Union[List[Tool], List[BaseTool]]
|
||||
) -> List[BaseTool]:
|
||||
agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
|
||||
if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
|
||||
if not tools:
|
||||
@@ -957,7 +992,7 @@ class Crew(BaseModel):
|
||||
tools = self._inject_delegation_tools(
|
||||
tools, task.agent, agents_for_delegation
|
||||
)
|
||||
return tools
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _log_task_start(self, task: Task, role: str = "None"):
|
||||
if self.output_log_file:
|
||||
@@ -965,7 +1000,9 @@ class Crew(BaseModel):
|
||||
task_name=task.name, task=task.description, agent=role, status="started"
|
||||
)
|
||||
|
||||
def _update_manager_tools(self, task: Task, tools: List[Tool]):
|
||||
def _update_manager_tools(
|
||||
self, task: Task, tools: Union[List[Tool], List[BaseTool]]
|
||||
) -> List[BaseTool]:
|
||||
if self.manager_agent:
|
||||
if task.agent:
|
||||
tools = self._inject_delegation_tools(tools, task.agent, [task.agent])
|
||||
@@ -973,7 +1010,7 @@ class Crew(BaseModel):
|
||||
tools = self._inject_delegation_tools(
|
||||
tools, self.manager_agent, self.agents
|
||||
)
|
||||
return tools
|
||||
return cast(List[BaseTool], tools)
|
||||
|
||||
def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
|
||||
context = (
|
||||
@@ -1214,13 +1251,14 @@ class Crew(BaseModel):
|
||||
def test(
|
||||
self,
|
||||
n_iterations: int,
|
||||
eval_llm: Union[str, InstanceOf[LLM]],
|
||||
eval_llm: Union[str, InstanceOf[BaseLLM]],
|
||||
inputs: Optional[Dict[str, Any]] = None,
|
||||
) -> None:
|
||||
"""Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
|
||||
try:
|
||||
eval_llm = create_llm(eval_llm)
|
||||
if not eval_llm:
|
||||
# Create LLM instance and ensure it's of type LLM for CrewEvaluator
|
||||
llm_instance = create_llm(eval_llm)
|
||||
if not llm_instance:
|
||||
raise ValueError("Failed to create LLM instance.")
|
||||
|
||||
crewai_event_bus.emit(
|
||||
@@ -1228,12 +1266,12 @@ class Crew(BaseModel):
|
||||
CrewTestStartedEvent(
|
||||
crew_name=self.name or "crew",
|
||||
n_iterations=n_iterations,
|
||||
eval_llm=eval_llm,
|
||||
eval_llm=llm_instance,
|
||||
inputs=inputs,
|
||||
),
|
||||
)
|
||||
test_crew = self.copy()
|
||||
evaluator = CrewEvaluator(test_crew, eval_llm) # type: ignore[arg-type]
|
||||
evaluator = CrewEvaluator(test_crew, llm_instance)
|
||||
|
||||
for i in range(1, n_iterations + 1):
|
||||
evaluator.set_iteration(i)
|
||||
|
||||
Reference in New Issue
Block a user