phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 04:00:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make all API methods async def again

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 16:50:57 -07:00
parent 95a96afe34
commit 627edaf407
17 changed files with 120 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/inference/client.py
View file

@ -42,10 +42,10 @@ class InferenceClient(Inference):
async def shutdown(self) -> None:
pass
def completion(self, request: CompletionRequest) -> AsyncGenerator:
async def completion(self, request: CompletionRequest) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -139,7 +139,8 @@ async def run_main(
else:
logprobs_config = None
iterator = client.chat_completion(
assert stream, "Non streaming not supported here"
iterator = await client.chat_completion(
model=model,
messages=[message],
stream=stream,

6
llama_stack/apis/inference/inference.py
View file

@ -181,10 +181,8 @@ 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")
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -196,7 +194,7 @@ class Inference(Protocol):
# 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")
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],