phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Fix precommit check after moving to ruff (#927)

Browse source 
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-02 09:46:45 -05:00 • committed by GitHub
parent 4773092dd1
commit 34ab7a3b6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
217 changed files with 981 additions and 2681 deletions
Download patch file Download diff file Expand all files Collapse all files

45
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -242,9 +242,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
else:
return await self._nonstream_chat_completion(request)
async def _get_params(
self, request: Union[ChatCompletionRequest, CompletionRequest]
) -> dict:
async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
sampling_options = get_sampling_options(request.sampling_params)
# This is needed since the Ollama API expects num_predict to be set
# for early truncation instead of max_tokens.
@ -255,14 +253,9 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
media_present = request_has_media(request)
if isinstance(request, ChatCompletionRequest):
if media_present:
contents = [
await convert_message_to_openai_dict_for_ollama(m)
for m in request.messages
]
contents = [await convert_message_to_openai_dict_for_ollama(m) for m in request.messages]
# flatten the list of lists
input_dict["messages"] = [
item for sublist in contents for item in sublist
]
input_dict["messages"] = [item for sublist in contents for item in sublist]
else:
input_dict["raw"] = True
input_dict["prompt"] = await chat_completion_request_to_prompt(
@ -271,12 +264,8 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
self.formatter,
)
else:
assert (
not media_present
), "Ollama does not support media for Completion requests"
input_dict["prompt"] = await completion_request_to_prompt(
request, self.formatter
)
assert not media_present, "Ollama does not support media for Completion requests"
input_dict["prompt"] = await completion_request_to_prompt(request, self.formatter)
input_dict["raw"] = True
if fmt := request.response_format:
@ -294,9 +283,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
"stream": request.stream,
}
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest
) -> ChatCompletionResponse:
async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse:
params = await self._get_params(request)
if "messages" in params:
r = await self.client.chat(**params)
@ -318,9 +305,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
)
return process_chat_completion_response(response, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest
) -> AsyncGenerator:
async def _stream_chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
params = await self._get_params(request)
async def _generate_and_convert_to_openai_compat():
@ -344,9 +329,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
)
stream = _generate_and_convert_to_openai_compat()
async for chunk in process_chat_completion_stream_response(
stream, self.formatter
):
async for chunk in process_chat_completion_stream_response(stream, self.formatter):
yield chunk
async def embeddings(
@ -356,9 +339,9 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
assert all(
not content_has_media(content) for content in contents
), "Ollama does not support media for embeddings"
assert all(not content_has_media(content) for content in contents), (
"Ollama does not support media for embeddings"
)
response = await self.client.embed(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
@ -395,11 +378,7 @@ async def convert_message_to_openai_dict_for_ollama(message: Message) -> List[di
if isinstance(content, ImageContentItem):
return {
"role": message.role,
"images": [
await convert_image_content_to_url(
content, download=True, include_format=False
)
],
"images": [await convert_image_content_to_url(content, download=True, include_format=False)],
}
else:
text = content.text if isinstance(content, TextContentItem) else content