phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 05:54:38 +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 16:10:35 -07:00
parent 80d58ab519
commit 579aa96b2c
42 changed files with 3147 additions and 202 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -12,8 +12,8 @@ from botocore.client import BaseClient
from llama_stack.apis.inference import (
ChatCompletionRequest,
Inference,
OpenAIChatCompletionRequest,
OpenAICompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAICompletionRequestWithExtraBody,
OpenAIEmbeddingsResponse,
)
from llama_stack.apis.inference.inference import (
@ -134,12 +134,12 @@ class BedrockInferenceAdapter(
async def openai_completion(
self,
params: OpenAICompletionRequest,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
raise NotImplementedError("OpenAI completion not supported by the Bedrock provider")
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
params: OpenAIChatCompletionRequestWithExtraBody,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
raise NotImplementedError("OpenAI chat completion not supported by the Bedrock provider")