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

refactor, body

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-10 13:47:36 -07:00
parent 6954fe2274
commit cb7fb0705b
33 changed files with 599 additions and 890 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,
@ -606,7 +608,8 @@ 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)
chat_params = OpenAIChatCompletionRequest(**request.body)
chat_response = await self.inference_api.openai_chat_completion(chat_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"
@ -620,7 +623,8 @@ class ReferenceBatchesImpl(Batches):
},
}
elif request.url == "/v1/completions":
completion_response = await self.inference_api.openai_completion(**request.body)
completion_params = OpenAICompletionRequest(**request.body)
completion_response = await self.inference_api.openai_completion(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"), (