phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-05 18:27:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

featu: support passing "extra body" throught to providers

Browse source 
# What does this PR do?
Allows passing through extra_body parameters to inference providers.


closes #2720

## Test Plan
CI and added new test
This commit is contained in:
Eric Huang 2025-10-10 13:47:36 -07:00
parent 361fcaf2f3
commit c40d8dcbee
3 changed files with 59 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -230,6 +230,9 @@ class LiteLLMOpenAIMixin(
) -> OpenAICompletion:
model_obj = await self.model_store.get_model(params.model)
# Extract extra fields
extra_body = dict(params.__pydantic_extra__ or {})
request_params = await prepare_openai_completion_params(
model=self.get_litellm_model_name(model_obj.provider_resource_id),
prompt=params.prompt,
@ -253,6 +256,7 @@ class LiteLLMOpenAIMixin(
suffix=params.suffix,
api_key=self.get_api_key(),
api_base=self.api_base,
**extra_body,
)
return await litellm.atext_completion(**request_params)
@ -272,6 +276,9 @@ class LiteLLMOpenAIMixin(
model_obj = await self.model_store.get_model(params.model)
# Extract extra fields
extra_body = dict(params.__pydantic_extra__ or {})
request_params = await prepare_openai_completion_params(
model=self.get_litellm_model_name(model_obj.provider_resource_id),
messages=params.messages,
@ -298,6 +305,7 @@ class LiteLLMOpenAIMixin(
user=params.user,
api_key=self.get_api_key(),
api_base=self.api_base,
**extra_body,
)
return await litellm.acompletion(**request_params)