phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 11:20:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Separate chat_completion stream and non-stream implementations

Browse source 
This is a pretty important requirement. The streaming response type is
an AsyncGenerator while the non-stream one is a single object. So far
this has worked _sometimes_ due to various pre-existing hacks (and in
some cases, just failed.)
This commit is contained in:
Ashwin Bharambe 2024-10-08 10:52:16 -07:00 • committed by Ashwin Bharambe
parent f8752ab8dc
commit 0c9eb3341c
5 changed files with 346 additions and 287 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/apis/inference/inference.py
View file

@ -180,8 +180,10 @@ class ModelStore(Protocol):
class Inference(Protocol):
model_store: ModelStore
# This method is not `async def` because it can result in either an
# `AsyncGenerator` or a `CompletionResponse` depending on the value of `stream`.
@webmethod(route="/inference/completion")
async def completion(
def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -190,8 +192,10 @@ class Inference(Protocol):
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]: ...
# This method is not `async def` because it can result in either an
# `AsyncGenerator` or a `ChatCompletionResponse` depending on the value of `stream`.
@webmethod(route="/inference/chat_completion")
async def chat_completion(
def chat_completion(
self,
model: str,
messages: List[Message],