forked from phoenix-oss/llama-stack-mirror
Fix precommit check after moving to ruff (#927)
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
GitHub
parent
4773092dd1
commit
34ab7a3b6c
217 changed files with 981 additions and 2681 deletions
|
|
@ -35,9 +35,7 @@ class NVIDIAConfig(BaseModel):
|
|||
"""
|
||||
|
||||
url: str = Field(
|
||||
default_factory=lambda: os.getenv(
|
||||
"NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"
|
||||
),
|
||||
default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"),
|
||||
description="A base url for accessing the NVIDIA NIM",
|
||||
)
|
||||
api_key: Optional[SecretStr] = Field(
|
||||
|
|
|
|||
|
|
@ -96,8 +96,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
if _is_nvidia_hosted(config):
|
||||
if not config.api_key:
|
||||
raise RuntimeError(
|
||||
"API key is required for hosted NVIDIA NIM. "
|
||||
"Either provide an API key or use a self-hosted NIM."
|
||||
"API key is required for hosted NVIDIA NIM. Either provide an API key or use a self-hosted NIM."
|
||||
)
|
||||
# elif self._config.api_key:
|
||||
#
|
||||
|
|
@ -113,11 +112,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
# make sure the client lives longer than any async calls
|
||||
self._client = AsyncOpenAI(
|
||||
base_url=f"{self._config.url}/v1",
|
||||
api_key=(
|
||||
self._config.api_key.get_secret_value()
|
||||
if self._config.api_key
|
||||
else "NO KEY"
|
||||
),
|
||||
api_key=(self._config.api_key.get_secret_value() if self._config.api_key else "NO KEY"),
|
||||
timeout=self._config.timeout,
|
||||
)
|
||||
|
||||
|
|
@ -150,9 +145,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
try:
|
||||
response = await self._client.completions.create(**request)
|
||||
except APIConnectionError as e:
|
||||
raise ConnectionError(
|
||||
f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}"
|
||||
) from e
|
||||
raise ConnectionError(f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}") from e
|
||||
|
||||
if stream:
|
||||
return convert_openai_completion_stream(response)
|
||||
|
|
@ -178,9 +171,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
tool_prompt_format: Optional[ToolPromptFormat] = None,
|
||||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
) -> Union[
|
||||
ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]
|
||||
]:
|
||||
) -> Union[ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]]:
|
||||
if tool_prompt_format:
|
||||
warnings.warn("tool_prompt_format is not supported by NVIDIA NIM, ignoring")
|
||||
|
||||
|
|
@ -204,9 +195,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
try:
|
||||
response = await self._client.chat.completions.create(**request)
|
||||
except APIConnectionError as e:
|
||||
raise ConnectionError(
|
||||
f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}"
|
||||
) from e
|
||||
raise ConnectionError(f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}") from e
|
||||
|
||||
if stream:
|
||||
return convert_openai_chat_completion_stream(response)
|
||||
|
|
|
|||
|
|
@ -185,9 +185,7 @@ async def _convert_message(message: Message | Dict) -> OpenAIChatCompletionMessa
|
|||
return content
|
||||
elif isinstance(content, ImageContentItem):
|
||||
return OpenAIChatCompletionContentPartImageParam(
|
||||
image_url=OpenAIImageURL(
|
||||
url=await convert_image_content_to_url(content)
|
||||
),
|
||||
image_url=OpenAIImageURL(url=await convert_image_content_to_url(content)),
|
||||
type="image_url",
|
||||
)
|
||||
elif isinstance(content, List):
|
||||
|
|
@ -260,12 +258,9 @@ async def convert_chat_completion_request(
|
|||
# stream -> stream
|
||||
# logprobs -> logprobs
|
||||
|
||||
if request.response_format and not isinstance(
|
||||
request.response_format, JsonSchemaResponseFormat
|
||||
):
|
||||
if request.response_format and not isinstance(request.response_format, JsonSchemaResponseFormat):
|
||||
raise ValueError(
|
||||
f"Unsupported response format: {request.response_format}. "
|
||||
"Only JsonSchemaResponseFormat is supported."
|
||||
f"Unsupported response format: {request.response_format}. Only JsonSchemaResponseFormat is supported."
|
||||
)
|
||||
|
||||
nvext = {}
|
||||
|
|
@ -286,9 +281,7 @@ async def convert_chat_completion_request(
|
|||
nvext.update(guided_json=request.response_format.json_schema)
|
||||
|
||||
if request.tools:
|
||||
payload.update(
|
||||
tools=[_convert_tooldef_to_openai_tool(tool) for tool in request.tools]
|
||||
)
|
||||
payload.update(tools=[_convert_tooldef_to_openai_tool(tool) for tool in request.tools])
|
||||
if request.tool_choice:
|
||||
payload.update(
|
||||
tool_choice=request.tool_choice.value
|
||||
|
|
@ -410,11 +403,7 @@ def _convert_openai_logprobs(
|
|||
return None
|
||||
|
||||
return [
|
||||
TokenLogProbs(
|
||||
logprobs_by_token={
|
||||
logprobs.token: logprobs.logprob for logprobs in content.top_logprobs
|
||||
}
|
||||
)
|
||||
TokenLogProbs(logprobs_by_token={logprobs.token: logprobs.logprob for logprobs in content.top_logprobs})
|
||||
for content in logprobs.content
|
||||
]
|
||||
|
||||
|
|
@ -452,17 +441,14 @@ def convert_openai_chat_completion_choice(
|
|||
end_of_message = "end_of_message"
|
||||
out_of_tokens = "out_of_tokens"
|
||||
"""
|
||||
assert (
|
||||
hasattr(choice, "message") and choice.message
|
||||
), "error in server response: message not found"
|
||||
assert (
|
||||
hasattr(choice, "finish_reason") and choice.finish_reason
|
||||
), "error in server response: finish_reason not found"
|
||||
assert hasattr(choice, "message") and choice.message, "error in server response: message not found"
|
||||
assert hasattr(choice, "finish_reason") and choice.finish_reason, (
|
||||
"error in server response: finish_reason not found"
|
||||
)
|
||||
|
||||
return ChatCompletionResponse(
|
||||
completion_message=CompletionMessage(
|
||||
content=choice.message.content
|
||||
or "", # CompletionMessage content is not optional
|
||||
content=choice.message.content or "", # CompletionMessage content is not optional
|
||||
stop_reason=_convert_openai_finish_reason(choice.finish_reason),
|
||||
tool_calls=_convert_openai_tool_calls(choice.message.tool_calls),
|
||||
),
|
||||
|
|
@ -479,9 +465,7 @@ async def convert_openai_chat_completion_stream(
|
|||
"""
|
||||
|
||||
# generate a stream of ChatCompletionResponseEventType: start -> progress -> progress -> ...
|
||||
def _event_type_generator() -> (
|
||||
Generator[ChatCompletionResponseEventType, None, None]
|
||||
):
|
||||
def _event_type_generator() -> Generator[ChatCompletionResponseEventType, None, None]:
|
||||
yield ChatCompletionResponseEventType.start
|
||||
while True:
|
||||
yield ChatCompletionResponseEventType.progress
|
||||
|
|
@ -532,18 +516,14 @@ async def convert_openai_chat_completion_stream(
|
|||
# it is possible to have parallel tool calls in stream, but
|
||||
# ChatCompletionResponseEvent only supports one per stream
|
||||
if len(choice.delta.tool_calls) > 1:
|
||||
warnings.warn(
|
||||
"multiple tool calls found in a single delta, using the first, ignoring the rest"
|
||||
)
|
||||
warnings.warn("multiple tool calls found in a single delta, using the first, ignoring the rest")
|
||||
|
||||
# NIM only produces fully formed tool calls, so we can assume success
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=next(event_type),
|
||||
delta=ToolCallDelta(
|
||||
tool_call=_convert_openai_tool_calls(choice.delta.tool_calls)[
|
||||
0
|
||||
],
|
||||
tool_call=_convert_openai_tool_calls(choice.delta.tool_calls)[0],
|
||||
parse_status=ToolCallParseStatus.succeeded,
|
||||
),
|
||||
logprobs=_convert_openai_logprobs(choice.logprobs),
|
||||
|
|
@ -618,10 +598,7 @@ def convert_completion_request(
|
|||
nvext.update(top_k=-1)
|
||||
payload.update(top_p=request.sampling_params.top_p)
|
||||
elif request.sampling_params.strategy == "top_k":
|
||||
if (
|
||||
request.sampling_params.top_k != -1
|
||||
and request.sampling_params.top_k < 1
|
||||
):
|
||||
if request.sampling_params.top_k != -1 and request.sampling_params.top_k < 1:
|
||||
warnings.warn("top_k must be -1 or >= 1")
|
||||
nvext.update(top_k=request.sampling_params.top_k)
|
||||
elif request.sampling_params.strategy == "greedy":
|
||||
|
|
@ -640,9 +617,7 @@ def _convert_openai_completion_logprobs(
|
|||
if not logprobs:
|
||||
return None
|
||||
|
||||
return [
|
||||
TokenLogProbs(logprobs_by_token=logprobs) for logprobs in logprobs.top_logprobs
|
||||
]
|
||||
return [TokenLogProbs(logprobs_by_token=logprobs) for logprobs in logprobs.top_logprobs]
|
||||
|
||||
|
||||
def convert_openai_completion_choice(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue