phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 05:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-09 20:53:19 -07:00
parent f50ce11a3b
commit 4a3d1e33f8
31 changed files with 727 additions and 892 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/inline/batches/reference/batches.py
View file

@ -22,6 +22,8 @@ from llama_stack.apis.files import Files, OpenAIFilePurpose
from llama_stack.apis.inference import (
Inference,
OpenAIAssistantMessageParam,
OpenaiChatCompletionRequest,
OpenAICompletionRequest,
OpenAIDeveloperMessageParam,
OpenAIMessageParam,
OpenAISystemMessageParam,
@ -601,7 +603,8 @@ class ReferenceBatchesImpl(Batches):
# TODO(SECURITY): review body for security issues
if request.url == "/v1/chat/completions":
request.body["messages"] = [convert_to_openai_message_param(msg) for msg in request.body["messages"]]
chat_response = await self.inference_api.openai_chat_completion(**request.body)
params = OpenaiChatCompletionRequest(**request.body)
chat_response = await self.inference_api.openai_chat_completion(params)
# this is for mypy, we don't allow streaming so we'll get the right type
assert hasattr(chat_response, "model_dump_json"), "Chat response must have model_dump_json method"
@ -615,7 +618,8 @@ class ReferenceBatchesImpl(Batches):
},
}
else: # /v1/completions
completion_response = await self.inference_api.openai_completion(**request.body)
params = OpenAICompletionRequest(**request.body)
completion_response = await self.inference_api.openai_completion(params)
# this is for mypy, we don't allow streaming so we'll get the right type
assert hasattr(completion_response, "model_dump_json"), (