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

21
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -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)