mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-15 11:08:33 +00:00
126b91eab3
* ruff linted * using native sdks with litellm fallback * drop exa * drop print on completion * Refactor LLM and utility functions for type consistency - Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`. - Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`. - Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety. - Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances. * fix agent_tests * fix litellm tests and usagemetrics fix * drop print * Refactor LLM event handling and improve test coverage - Removed commented-out event emission for LLM call failures in `llm.py`. - Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses. - Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity. - Updated agent and task ID assertions in tests to ensure they are consistently treated as strings. * fix test_converter * fixed tests/agents/test_agent.py * Refactor LLM context length exception handling and improve provider integration - Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency. - Updated LLM class to pass the provider parameter correctly during initialization. - Enhanced error handling in various LLM provider implementations to raise the new exception type. - Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios. * Enhance LLM context window handling across providers - Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs. - Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits. - Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models. - Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility. * fix test agent again * fix test agent * feat: add native LLM providers for Anthropic, Azure, and Gemini - Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs. - Added utility functions for tool validation and extraction to support function calling across LLM providers. - Enhanced context window management and token usage extraction for each provider. - Created a common utility module for shared functionality among LLM providers. * chore: update dependencies and improve context management - Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity. - Updated the `litellm` dependency specification to allow for greater flexibility in versioning. - Refactored context length exception handling across various LLM providers to use a consistent error class. - Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems. * refactor(tests): update LLM instantiation to include is_litellm flag in test cases - Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class. - This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios. - Adjusted relevant assertions and comments to reflect the updated LLM behavior. * linter * linted * revert constants * fix(tests): correct type hint in expected model description - Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions. - This change ensures that the test accurately reflects the expected output format for model descriptions. * refactor(llm): enhance LLM instantiation and error handling - Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string. - Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM. - Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration. - Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios. * fixed test * refactor(llm): enhance token usage tracking and add copy methods - Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities. - Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters. - Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration. * refactor(tests): reorganize imports and enhance error messages in test cases - Cleaned up import statements in test_crew.py for better organization and readability. - Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling. - Adjusted comments for clarity and consistency across test scenarios. - Ensured that all necessary modules are imported correctly to avoid potential runtime issues.
86 lines
3.0 KiB
Python
86 lines
3.0 KiB
Python
"""Token counting callback handler for LLM interactions.
|
|
|
|
This module provides a callback handler that tracks token usage
|
|
for LLM API calls through the litellm library.
|
|
"""
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
from litellm.integrations.custom_logger import CustomLogger
|
|
from litellm.types.utils import Usage
|
|
else:
|
|
try:
|
|
from litellm.integrations.custom_logger import CustomLogger
|
|
from litellm.types.utils import Usage
|
|
except ImportError:
|
|
|
|
class CustomLogger:
|
|
"""Fallback CustomLogger when litellm is not available."""
|
|
|
|
class Usage:
|
|
"""Fallback Usage when litellm is not available."""
|
|
|
|
|
|
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
|
|
from crewai.utilities.logger_utils import suppress_warnings
|
|
|
|
|
|
class TokenCalcHandler(CustomLogger):
|
|
"""Handler for calculating and tracking token usage in LLM calls.
|
|
|
|
This handler integrates with litellm's logging system to track
|
|
prompt tokens, completion tokens, and cached tokens across requests.
|
|
|
|
Attributes:
|
|
token_cost_process: The token process tracker to accumulate usage metrics.
|
|
"""
|
|
|
|
def __init__(self, token_cost_process: TokenProcess | None, **kwargs: Any) -> None:
|
|
"""Initialize the token calculation handler.
|
|
|
|
Args:
|
|
token_cost_process: Optional token process tracker for accumulating metrics.
|
|
"""
|
|
super().__init__(**kwargs)
|
|
self.token_cost_process = token_cost_process
|
|
|
|
def log_success_event(
|
|
self,
|
|
kwargs: dict[str, Any],
|
|
response_obj: dict[str, Any],
|
|
start_time: float,
|
|
end_time: float,
|
|
) -> None:
|
|
"""Log successful LLM API call and track token usage.
|
|
|
|
Args:
|
|
kwargs: The arguments passed to the LLM call.
|
|
response_obj: The response object from the LLM API.
|
|
start_time: The timestamp when the call started.
|
|
end_time: The timestamp when the call completed.
|
|
"""
|
|
if self.token_cost_process is None:
|
|
return
|
|
|
|
with suppress_warnings():
|
|
if isinstance(response_obj, dict) and "usage" in response_obj:
|
|
usage: Usage = response_obj["usage"]
|
|
if usage:
|
|
self.token_cost_process.sum_successful_requests(1)
|
|
if hasattr(usage, "prompt_tokens"):
|
|
self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
|
|
if hasattr(usage, "completion_tokens"):
|
|
self.token_cost_process.sum_completion_tokens(
|
|
usage.completion_tokens
|
|
)
|
|
if (
|
|
hasattr(usage, "prompt_tokens_details")
|
|
and usage.prompt_tokens_details
|
|
and usage.prompt_tokens_details.cached_tokens
|
|
):
|
|
self.token_cost_process.sum_cached_prompt_tokens(
|
|
usage.prompt_tokens_details.cached_tokens
|
|
)
|