phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add tools to chat completion request

Browse source
This commit is contained in:
Hardik Shah 2024-08-21 17:48:48 -07:00
parent 863bb915e1
commit f3f7af7b8a
26 changed files with 558 additions and 226 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_toolchain/inference/meta_reference/inference.py
View file

@ -22,7 +22,7 @@ from llama_toolchain.inference.api import (
ToolCallDelta,
ToolCallParseStatus,
)
from llama_toolchain.inference.prepare_messages import prepare_messages_for_tools
from .config import MetaReferenceImplConfig
from .model_parallel import LlamaModelParallelGenerator
@ -67,6 +67,7 @@ class MetaReferenceInferenceImpl(Inference):
) -> AsyncIterator[
Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
]:
request = prepare_messages_for_tools(request)
model = resolve_model(request.model)
if model is None:
raise RuntimeError(