phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 13:57:57 +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 15:42:51 -07:00
parent cb7fb0705b
commit 0ed59497bc
35 changed files with 1893 additions and 200 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -9,8 +9,8 @@ from collections.abc import AsyncIterator
from llama_stack.apis.inference import (
InferenceProvider,
OpenAIChatCompletionRequest,
OpenAICompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAICompletionRequestWithExtraBody,
)
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
@ -67,7 +67,7 @@ class MetaReferenceInferenceImpl(
async def openai_completion(
self,
params: OpenAICompletionRequest,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
raise NotImplementedError("OpenAI completion not supported by meta reference provider")
@ -153,6 +153,6 @@ class MetaReferenceInferenceImpl(
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
params: OpenAIChatCompletionRequestWithExtraBody,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
raise NotImplementedError("OpenAI chat completion not supported by meta-reference inference provider")

8
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -8,8 +8,8 @@ from collections.abc import AsyncIterator
from llama_stack.apis.inference import (
InferenceProvider,
OpenAIChatCompletionRequest,
OpenAICompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAICompletionRequestWithExtraBody,
)
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
@ -72,12 +72,12 @@ class SentenceTransformersInferenceImpl(
async def openai_completion(
self,
params: OpenAICompletionRequest,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
raise NotImplementedError("OpenAI completion not supported by sentence transformers provider")
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
params: OpenAIChatCompletionRequestWithExtraBody,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
raise NotImplementedError("OpenAI chat completion not supported by sentence transformers provider")