diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 084b53cd904..70d5b443974 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -5632,9 +5632,10 @@ def emit_standard_logging_payload(payload: StandardLoggingPayload): try: print(json.dumps(payload, indent=4, default=str)) # noqa except Exception as e: - print( - "Error serializing standard logging payload for debug output:", - str(e), + verbose_logger.exception( + "Error serializing standard logging payload for debug output: {}".format( + str(e) + ) ) diff --git a/litellm/llms/gigachat/authenticator.py b/litellm/llms/gigachat/authenticator.py index ce6d4b3eca9..a20da943ee1 100644 --- a/litellm/llms/gigachat/authenticator.py +++ b/litellm/llms/gigachat/authenticator.py @@ -147,9 +147,7 @@ async def get_access_token_async( ) scope = scope or litellm_params.get("gigachat_scope") or _get_scope() - auth_url = ( - auth_url or litellm_params.get("gigachat_auth_url") or _get_auth_url() - ) + auth_url = auth_url or litellm_params.get("gigachat_auth_url") or _get_auth_url() # Check cache cache_key = f"gigachat_token:{credentials[:16]}" diff --git a/litellm/llms/gigachat/chat/streaming.py b/litellm/llms/gigachat/chat/streaming.py index 2fd5fc22b01..9ef29b2c6cb 100644 --- a/litellm/llms/gigachat/chat/streaming.py +++ b/litellm/llms/gigachat/chat/streaming.py @@ -76,7 +76,11 @@ class GigaChatModelResponseIterator: usage_data = chunk.get("usage", {}) if usage_data: usage = convert_usage(usage_data) - usage_block = ChatCompletionUsageBlock(**usage.dict()) + usage_block = ChatCompletionUsageBlock( + prompt_tokens=usage.prompt_tokens, + completion_tokens=usage.completion_tokens, + total_tokens=usage.total_tokens, + ) if finish_reason is not None: is_finished = True diff --git a/litellm/llms/gigachat/passthrough/transformation.py b/litellm/llms/gigachat/passthrough/transformation.py index 43669355f2b..ff2c4ad4986 100644 --- a/litellm/llms/gigachat/passthrough/transformation.py +++ b/litellm/llms/gigachat/passthrough/transformation.py @@ -93,44 +93,50 @@ class GigaChatPassthroughConfig(BasePassthroughConfig): if provider_chat_config is None: raise ValueError(f"No provider config found for model: {model}") - litellm_model_response: ModelResponse = provider_chat_config.transform_response( - model=model, - messages=request_data.get("messages", []), - raw_response=httpx_response, - model_response=ModelResponse(), - logging_obj=logging_obj, - optional_params={}, - litellm_params={}, - api_key="", - request_data=request_data, - encoding=encoding, + litellm_model_response: ModelResponse = ( + provider_chat_config.transform_response( + model=model, + messages=request_data.get("messages", []), + raw_response=httpx_response, + model_response=ModelResponse(), + logging_obj=logging_obj, + optional_params={}, + litellm_params={}, + api_key="", + request_data=request_data, + encoding=encoding, + ) ) return litellm_model_response - + if "embeddings" in endpoint: - - provider_embedding_config = ProviderConfigManager.get_provider_embedding_config( - provider=LlmProviders(custom_llm_provider), - model=model, + + provider_embedding_config = ( + ProviderConfigManager.get_provider_embedding_config( + provider=LlmProviders(custom_llm_provider), + model=model, + ) ) if provider_embedding_config is None: raise ValueError(f"No provider config found for model: {model}") - litellm_embedding_response: EmbeddingResponse = provider_embedding_config.transform_embedding_response( - model=model, - raw_response=httpx_response, - model_response=EmbeddingResponse(), - logging_obj=logging_obj, - optional_params={}, - api_key="", - request_data=request_data, - litellm_params={}, + litellm_embedding_response: EmbeddingResponse = ( + provider_embedding_config.transform_embedding_response( + model=model, + raw_response=httpx_response, + model_response=EmbeddingResponse(), + logging_obj=logging_obj, + optional_params={}, + api_key="", + request_data=request_data, + litellm_params={}, + ) ) return litellm_embedding_response - + return None def handle_logging_collected_chunks( diff --git a/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py b/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py index 15852890eec..46d8b32369f 100644 --- a/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py +++ b/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py @@ -2461,7 +2461,7 @@ async def gigachat_proxy_route( is_router_model = False model = request_body.get("model") - if model: + if model: is_router_model = is_passthrough_request_using_router_model( request_body, llm_router ) @@ -2470,7 +2470,6 @@ async def gigachat_proxy_route( status_code=400, detail={"error": "Model is required in request body"} ) - # If router model, use dedicated router passthrough handler # This uses the same common processing path as non-router models if model and is_router_model and llm_router: @@ -2582,8 +2581,6 @@ async def handle_gigachat_passthrough_router_model( Returns: Response or StreamingResponse depending on endpoint type """ - from fastapi import Response as FastAPIResponse - from litellm.proxy.common_request_processing import ProxyBaseLLMRequestProcessing # Detect streaming based on request body @@ -2628,7 +2625,13 @@ async def handle_gigachat_passthrough_router_model( data["custom_llm_provider"] = "gigachat" # Remove sensitive keys from data - keys = ["gigachat_auth_url", "gigachat_access_token", "gigachat_scope", "api_base", "api_key"] + keys = [ + "gigachat_auth_url", + "gigachat_access_token", + "gigachat_scope", + "api_base", + "api_key", + ] for key in keys: data.pop(key, None)