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>

src/crewai/llms/base_llm.py

@@ -0,0 +1,91 @@
+from abc import ABC, abstractmethod
+from typing import Any, Callable, Dict, List, Optional, Union
+
+
+class BaseLLM(ABC):
+    """Abstract base class for LLM implementations.
+
+    This class defines the interface that all LLM implementations must follow.
+    Users can extend this class to create custom LLM implementations that don't
+    rely on litellm's authentication mechanism.
+
+    Custom LLM implementations should handle error cases gracefully, including
+    timeouts, authentication failures, and malformed responses. They should also
+    implement proper validation for input parameters and provide clear error
+    messages when things go wrong.
+
+    Attributes:
+        stop (list): A list of stop sequences that the LLM should use to stop generation.
+            This is used by the CrewAgentExecutor and other components.
+    """
+
+    model: str
+    temperature: Optional[float] = None
+    stop: Optional[List[str]] = None
+
+    def __init__(
+        self,
+        model: str,
+        temperature: Optional[float] = None,
+    ):
+        """Initialize the BaseLLM with default attributes.
+
+        This constructor sets default values for attributes that are expected
+        by the CrewAgentExecutor and other components.
+
+        All custom LLM implementations should call super().__init__() to ensure
+        that these default attributes are properly initialized.
+        """
+        self.model = model
+        self.temperature = temperature
+        self.stop = []
+
+    @abstractmethod
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Call the LLM with the given messages.
+
+        Args:
+            messages: Input messages for the LLM.
+                     Can be a string or list of message dictionaries.
+                     If string, it will be converted to a single user message.
+                     If list, each dict must have 'role' and 'content' keys.
+            tools: Optional list of tool schemas for function calling.
+                  Each tool should define its name, description, and parameters.
+            callbacks: Optional list of callback functions to be executed
+                      during and after the LLM call.
+            available_functions: Optional dict mapping function names to callables
+                               that can be invoked by the LLM.
+
+        Returns:
+            Either a text response from the LLM (str) or
+            the result of a tool function call (Any).
+
+        Raises:
+            ValueError: If the messages format is invalid.
+            TimeoutError: If the LLM request times out.
+            RuntimeError: If the LLM request fails for other reasons.
+        """
+        pass
+
+    def supports_stop_words(self) -> bool:
+        """Check if the LLM supports stop words.
+
+        Returns:
+            bool: True if the LLM supports stop words, False otherwise.
+        """
+        return True  # Default implementation assumes support for stop words
+
+    def get_context_window_size(self) -> int:
+        """Get the context window size for the LLM.
+
+        Returns:
+            int: The number of tokens/characters the model can handle.
+        """
+        # Default implementation - subclasses should override with model-specific values
+        return 4096

src/crewai/llms/third_party/ai_suite.py

@@ -0,0 +1,38 @@
+from typing import Any, Dict, List, Optional, Union
+
+import aisuite as ai
+
+from crewai.llms.base_llm import BaseLLM
+
+
+class AISuiteLLM(BaseLLM):
+    def __init__(self, model: str, temperature: Optional[float] = None, **kwargs):
+        super().__init__(model, temperature, **kwargs)
+        self.client = ai.Client()
+
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        completion_params = self._prepare_completion_params(messages, tools)
+        response = self.client.chat.completions.create(**completion_params)
+
+        return response.choices[0].message.content
+
+    def _prepare_completion_params(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+    ) -> Dict[str, Any]:
+        return {
+            "model": self.model,
+            "messages": messages,
+            "temperature": self.temperature,
+            "tools": tools,
+        }
+
+    def supports_function_calling(self) -> bool:
+        return False