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

5
llama_stack/providers/inline/tool_runtime/rag/context_retriever.py
View file

@ -8,7 +8,7 @@
from jinja2 import Template
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import OpenAIUserMessageParam
from llama_stack.apis.inference import OpenaiChatCompletionRequest, OpenAIUserMessageParam
from llama_stack.apis.tools.rag_tool import (
DefaultRAGQueryGeneratorConfig,
LLMRAGQueryGeneratorConfig,
@ -65,11 +65,12 @@ async def llm_rag_query_generator(
model = config.model
message = OpenAIUserMessageParam(content=rendered_content)
response = await inference_api.openai_chat_completion(
params = OpenaiChatCompletionRequest(
model=model,
messages=[message],
stream=False,
)
response = await inference_api.openai_chat_completion(params)
query = response.choices[0].message.content