phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-07 22:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make all methods async def again; add completion() for meta-reference (#270)

Browse source 
PR #201 had made several changes while trying to fix issues with getting the stream=False branches of inference and agents API working. As part of this, it made a change which was slightly gratuitous. Namely, making chat_completion() and brethren "def" instead of "async def".

The rationale was that this allowed the user (within llama-stack) of this to use it as:

```
async for chunk in api.chat_completion(params)
```

However, it causes unnecessary confusion for several folks. Given that clients (e.g., llama-stack-apps) anyway use the SDK methods (which are completely isolated) this choice was not ideal. Let's revert back so the call now looks like:

```
async for chunk in await api.chat_completion(params)
```

Bonus: Added a completion() implementation for the meta-reference provider. Technically should have been another PR :)
This commit is contained in:
Ashwin Bharambe 2024-10-18 20:50:59 -07:00 • committed by GitHub
parent 95a96afe34
commit 2089427d60
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 330 additions and 213 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/adapters/inference/bedrock/bedrock.py
View file

@ -47,7 +47,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
async def shutdown(self) -> None:
self.client.close()
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -283,7 +283,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
)
return tool_config
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],

6
llama_stack/providers/adapters/inference/databricks/databricks.py
View file

@ -48,7 +48,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
async def shutdown(self) -> None:
pass
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -58,7 +58,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -84,7 +84,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
if stream:
return self._stream_chat_completion(request, client)
else:
return self._nonstream_chat_completion(request, client)
return await self._nonstream_chat_completion(request, client)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, client: OpenAI

6
llama_stack/providers/adapters/inference/fireworks/fireworks.py
View file

@ -51,7 +51,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
async def shutdown(self) -> None:
pass
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -61,7 +61,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -87,7 +87,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
if stream:
return self._stream_chat_completion(request, client)
else:
return self._nonstream_chat_completion(request, client)
return await self._nonstream_chat_completion(request, client)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, client: Fireworks

6
llama_stack/providers/adapters/inference/ollama/ollama.py
View file

@ -84,7 +84,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
return ret
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -94,7 +94,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -118,7 +118,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
if stream:
return self._stream_chat_completion(request)
else:
return self._nonstream_chat_completion(request)
return await self._nonstream_chat_completion(request)
def _get_params(self, request: ChatCompletionRequest) -> dict:
return {

6
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -66,7 +66,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def shutdown(self) -> None:
pass
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -76,7 +76,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -101,7 +101,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
if stream:
return self._stream_chat_completion(request)
else:
return self._nonstream_chat_completion(request)
return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest

4
llama_stack/providers/adapters/inference/together/together.py
View file

@ -64,7 +64,7 @@ class TogetherInferenceAdapter(
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -101,7 +101,7 @@ class TogetherInferenceAdapter(
if stream:
return self._stream_chat_completion(request, client)
else:
return self._nonstream_chat_completion(request, client)
return await self._nonstream_chat_completion(request, client)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, client: Together