mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
add tools to chat completion request
This commit is contained in:
parent
863bb915e1
commit
f3f7af7b8a
26 changed files with 558 additions and 226 deletions
|
@ -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(
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue