litellm-mirror/litellm/llms/openrouter/chat/transformation.py
Krish Dholakia f899b828cf
Support openrouter reasoning_content on streaming (#9094)
* feat(convert_dict_to_response.py): support openrouter format of reasoning content

* fix(transformation.py): fix openrouter streaming with reasoning content

Fixes https://github.com/BerriAI/litellm/issues/8193#issuecomment-270892962

* fix: fix type error
2025-03-09 20:03:59 -07:00

88 lines
2.8 KiB
Python

"""
Support for OpenAI's `/v1/chat/completions` endpoint.
Calls done in OpenAI/openai.py as OpenRouter is openai-compatible.
Docs: https://openrouter.ai/docs/parameters
"""
from typing import Any, AsyncIterator, Iterator, Optional, Union
import httpx
from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.types.utils import ModelResponse, ModelResponseStream
from ...openai.chat.gpt_transformation import OpenAIGPTConfig
from ..common_utils import OpenRouterException
class OpenrouterConfig(OpenAIGPTConfig):
def map_openai_params(
self,
non_default_params: dict,
optional_params: dict,
model: str,
drop_params: bool,
) -> dict:
mapped_openai_params = super().map_openai_params(
non_default_params, optional_params, model, drop_params
)
# OpenRouter-only parameters
extra_body = {}
transforms = non_default_params.pop("transforms", None)
models = non_default_params.pop("models", None)
route = non_default_params.pop("route", None)
if transforms is not None:
extra_body["transforms"] = transforms
if models is not None:
extra_body["models"] = models
if route is not None:
extra_body["route"] = route
mapped_openai_params["extra_body"] = (
extra_body # openai client supports `extra_body` param
)
return mapped_openai_params
def get_error_class(
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
) -> BaseLLMException:
return OpenRouterException(
message=error_message,
status_code=status_code,
headers=headers,
)
def get_model_response_iterator(
self,
streaming_response: Union[Iterator[str], AsyncIterator[str], ModelResponse],
sync_stream: bool,
json_mode: Optional[bool] = False,
) -> Any:
return OpenRouterChatCompletionStreamingHandler(
streaming_response=streaming_response,
sync_stream=sync_stream,
json_mode=json_mode,
)
class OpenRouterChatCompletionStreamingHandler(BaseModelResponseIterator):
def chunk_parser(self, chunk: dict) -> ModelResponseStream:
try:
new_choices = []
for choice in chunk["choices"]:
choice["delta"]["reasoning_content"] = choice["delta"].get("reasoning")
new_choices.append(choice)
return ModelResponseStream(
id=chunk["id"],
object="chat.completion.chunk",
created=chunk["created"],
model=chunk["model"],
choices=new_choices,
)
except Exception as e:
raise e