phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 11:08:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix passthrough impl, response.content.text

Browse source
This commit is contained in:
Yang Yang 2025-03-16 23:17:11 -07:00
parent a626b7bce3
commit af20652677
1 changed files with 9 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -12,6 +12,7 @@ from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
CompletionMessage,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
@ -160,12 +161,14 @@ class PassthroughInferenceAdapter(Inference):
client = self._get_client()
response = await client.inference.chat_completion(**json_params)
response = response.to_dict()
# temporary hack to remove the metrics from the response
response["metrics"] = []
return convert_to_pydantic(ChatCompletionResponse, response)
return ChatCompletionResponse(
completion_message=CompletionMessage(
content=response.completion_message.content.text,
stop_reason=response.completion_message.stop_reason,
tool_calls=response.completion_message.tool_calls,
),
logprobs=response.logprobs,
)
async def _stream_chat_completion(self, json_params: Dict[str, Any]) -> AsyncGenerator:
client = self._get_client()