phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Deepseek r1 support + watsonx qa improvements (#7907)

Browse source 
* 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
This commit is contained in:
Krish Dholakia 2025-01-21 23:13:15 -08:00 • committed by GitHub
parent 26a79a533d
commit 76795dba39
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 281 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py
View file

@ -337,7 +337,6 @@ def convert_to_model_response_object( # noqa: PLR0915
] = None, # used for supporting 'json_schema' on older models
):
received_args = locals()
additional_headers = get_response_headers(_response_headers)
if hidden_params is None:
@ -411,12 +410,18 @@ def convert_to_model_response_object( # noqa: PLR0915
message = litellm.Message(content=json_mode_content_str)
finish_reason = "stop"
if message is None:
provider_specific_fields = {}
message_keys = Message.model_fields.keys()
for field in choice["message"].keys():
if field not in message_keys:
provider_specific_fields[field] = choice["message"][field]
message = Message(
content=choice["message"].get("content", None),
role=choice["message"]["role"] or "assistant",
function_call=choice["message"].get("function_call", None),
tool_calls=tool_calls,
audio=choice["message"].get("audio", None),
provider_specific_fields=provider_specific_fields,
)
finish_reason = choice.get("finish_reason", None)
if finish_reason is None: