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/fireworks/fireworks.py
View file

@ -95,9 +95,7 @@ MODEL_ALIASES = [
]
class FireworksInferenceAdapter(
ModelRegistryHelper, Inference, NeedsRequestProviderData
):
class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
def __init__(self, config: FireworksImplConfig) -> None:
ModelRegistryHelper.__init__(self, MODEL_ALIASES)
self.config = config
@ -147,9 +145,7 @@ class FireworksInferenceAdapter(
else:
return await self._nonstream_completion(request)
async def _nonstream_completion(
self, request: CompletionRequest
) -> CompletionResponse:
async def _nonstream_completion(self, request: CompletionRequest) -> CompletionResponse:
params = await self._get_params(request)
r = await self._get_client().completion.acreate(**params)
return process_completion_response(r, self.formatter)
@ -227,9 +223,7 @@ class FireworksInferenceAdapter(
else:
return await self._nonstream_chat_completion(request)
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._get_client().chat.completions.acreate(**params)
@ -237,9 +231,7 @@ class FireworksInferenceAdapter(
r = await self._get_client().completion.acreate(**params)
return process_chat_completion_response(r, 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 _to_async_generator():
@ -251,34 +243,25 @@ class FireworksInferenceAdapter(
yield chunk
stream = _to_async_generator()
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 _get_params(
self, request: Union[ChatCompletionRequest, CompletionRequest]
) -> dict:
async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
input_dict = {}
media_present = request_has_media(request)
if isinstance(request, ChatCompletionRequest):
if media_present:
input_dict["messages"] = [
await convert_message_to_openai_dict(m, download=True)
for m in request.messages
await convert_message_to_openai_dict(m, download=True) for m in request.messages
]
else:
input_dict["prompt"] = await chat_completion_request_to_prompt(
request, self.get_llama_model(request.model), self.formatter
)
else:
assert (
not media_present
), "Fireworks does not support media for Completion requests"
input_dict["prompt"] = await completion_request_to_prompt(
request, self.formatter
)
assert not media_present, "Fireworks does not support media for Completion requests"
input_dict["prompt"] = await completion_request_to_prompt(request, self.formatter)
# Fireworks always prepends with BOS
if "prompt" in input_dict:
@ -289,9 +272,7 @@ class FireworksInferenceAdapter(
"model": request.model,
**input_dict,
"stream": request.stream,
**self._build_options(
request.sampling_params, request.response_format, request.logprobs
),
**self._build_options(request.sampling_params, request.response_format, request.logprobs),
}
async def embeddings(
@ -304,9 +285,9 @@ class FireworksInferenceAdapter(
kwargs = {}
if model.metadata.get("embedding_dimensions"):
kwargs["dimensions"] = model.metadata.get("embedding_dimensions")
assert all(
not content_has_media(content) for content in contents
), "Fireworks does not support media for embeddings"
assert all(not content_has_media(content) for content in contents), (
"Fireworks does not support media for embeddings"
)
response = self._get_client().embeddings.create(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],