phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 21:58:38 +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

9
llama_stack/providers/remote/inference/llama_openai_compat/llama.py
View file

@ -3,7 +3,12 @@
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from llama_stack.apis.inference.inference import OpenAICompletion, OpenAICompletionRequest, OpenAIEmbeddingsResponse
from llama_stack.apis.inference.inference import (
OpenAICompletion,
OpenAICompletionRequestWithExtraBody,
OpenAIEmbeddingsResponse,
)
from llama_stack.log import get_logger
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
@ -29,7 +34,7 @@ class LlamaCompatInferenceAdapter(OpenAIMixin):
async def openai_completion(
self,
params: OpenAICompletionRequest,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
raise NotImplementedError()