mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
76795dba39
* fix(types/utils.py): support returning 'reasoning_content' for deepseek models Fixes https://github.com/BerriAI/litellm/issues/7877#issuecomment-2603813218 * fix(convert_dict_to_response.py): return deepseek response in provider_specific_field allows for separating openai vs. non-openai params in model response * fix(utils.py): support 'provider_specific_field' in delta chunk as well allows deepseek reasoning content chunk to be returned to user from stream as well Fixes https://github.com/BerriAI/litellm/issues/7877#issuecomment-2603813218 * fix(watsonx/chat/handler.py): fix passing space id to watsonx on chat route * fix(watsonx/): fix watsonx_text/ route with space id * fix(watsonx/): qa item - also adds better unit testing for watsonx embedding calls * fix(utils.py): rename to '..fields' * fix: fix linting errors * fix(utils.py): fix typing - don't show provider-specific field if none or empty - prevents default respons e from being non-oai compatible * fix: cleanup unused imports * docs(deepseek.md): add docs for deepseek reasoning model
89 lines
2.8 KiB
Python
89 lines
2.8 KiB
Python
from typing import Callable, Optional, Union
|
|
|
|
import httpx
|
|
|
|
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
|
|
from litellm.types.utils import CustomStreamingDecoder, ModelResponse
|
|
|
|
from ...openai_like.chat.handler import OpenAILikeChatHandler
|
|
from ..common_utils import _get_api_params
|
|
from .transformation import IBMWatsonXChatConfig
|
|
|
|
watsonx_chat_transformation = IBMWatsonXChatConfig()
|
|
|
|
|
|
class WatsonXChatHandler(OpenAILikeChatHandler):
|
|
def __init__(self, **kwargs):
|
|
super().__init__(**kwargs)
|
|
|
|
def completion(
|
|
self,
|
|
*,
|
|
model: str,
|
|
messages: list,
|
|
api_base: str,
|
|
custom_llm_provider: str,
|
|
custom_prompt_dict: dict,
|
|
model_response: ModelResponse,
|
|
print_verbose: Callable,
|
|
encoding,
|
|
api_key: Optional[str],
|
|
logging_obj,
|
|
optional_params: dict,
|
|
acompletion=None,
|
|
litellm_params=None,
|
|
headers: Optional[dict] = None,
|
|
logger_fn=None,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
|
|
custom_endpoint: Optional[bool] = None,
|
|
streaming_decoder: Optional[CustomStreamingDecoder] = None,
|
|
fake_stream: bool = False,
|
|
):
|
|
api_params = _get_api_params(params=optional_params)
|
|
|
|
## UPDATE HEADERS
|
|
headers = watsonx_chat_transformation.validate_environment(
|
|
headers=headers or {},
|
|
model=model,
|
|
messages=messages,
|
|
optional_params=optional_params,
|
|
api_key=api_key,
|
|
)
|
|
|
|
## UPDATE PAYLOAD (optional params)
|
|
watsonx_auth_payload = watsonx_chat_transformation._prepare_payload(
|
|
model=model,
|
|
api_params=api_params,
|
|
)
|
|
optional_params.update(watsonx_auth_payload)
|
|
|
|
## GET API URL
|
|
api_base = watsonx_chat_transformation.get_complete_url(
|
|
api_base=api_base,
|
|
model=model,
|
|
optional_params=optional_params,
|
|
stream=optional_params.get("stream", False),
|
|
)
|
|
|
|
return super().completion(
|
|
model=model,
|
|
messages=messages,
|
|
api_base=api_base,
|
|
custom_llm_provider=custom_llm_provider,
|
|
custom_prompt_dict=custom_prompt_dict,
|
|
model_response=model_response,
|
|
print_verbose=print_verbose,
|
|
encoding=encoding,
|
|
api_key=api_key,
|
|
logging_obj=logging_obj,
|
|
optional_params=optional_params,
|
|
acompletion=acompletion,
|
|
litellm_params=litellm_params,
|
|
logger_fn=logger_fn,
|
|
headers=headers,
|
|
timeout=timeout,
|
|
client=client,
|
|
custom_endpoint=True,
|
|
streaming_decoder=streaming_decoder,
|
|
)
|