phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: turn OpenAIMixin into a pydantic.BaseModel

Browse source 
- implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key
 - remove use of LiteLLMOpenAIMixin
 - add default initialize/shutdown methods to OpenAIMixin
 - remove __init__s to allow proper pydantic construction
 - remove dead code from vllm adapter and associated / duplicate unit tests
 - update vllm adapter to use openaimixin for model registration
 - remove ModelRegistryHelper from fireworks & together adapters
 - remove Inference from nvidia adapter
 - complete type hints on embedding_model_metadata
 - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc
 - new recordings for ollama
This commit is contained in:
Matthew Farrellee 2025-10-02 20:47:54 -04:00
parent ce77c27ff8
commit 60f0056cbc
57 changed files with 12520 additions and 1254 deletions
Download patch file Download diff file Expand all files Collapse all files

30
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -8,7 +8,6 @@
from openai import NOT_GIVEN
from llama_stack.apis.inference import (
Inference,
OpenAIEmbeddingData,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
@ -22,7 +21,9 @@ from .utils import _is_nvidia_hosted
logger = get_logger(name=__name__, category="inference::nvidia")
class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
class NVIDIAInferenceAdapter(OpenAIMixin):
config: NVIDIAConfig
"""
NVIDIA Inference Adapter for Llama Stack.
@ -37,32 +38,21 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
"""
# source: https://docs.nvidia.com/nim/nemo-retriever/text-embedding/latest/support-matrix.html
embedding_model_metadata = {
embedding_model_metadata: dict[str, dict[str, int]] = {
"nvidia/llama-3.2-nv-embedqa-1b-v2": {"embedding_dimension": 2048, "context_length": 8192},
"nvidia/nv-embedqa-e5-v5": {"embedding_dimension": 512, "context_length": 1024},
"nvidia/nv-embedqa-mistral-7b-v2": {"embedding_dimension": 512, "context_length": 4096},
"snowflake/arctic-embed-l": {"embedding_dimension": 512, "context_length": 1024},
}
def __init__(self, config: NVIDIAConfig) -> None:
logger.info(f"Initializing NVIDIAInferenceAdapter({config.url})...")
async def initialize(self) -> None:
logger.info(f"Initializing NVIDIAInferenceAdapter({self.config.url})...")
if _is_nvidia_hosted(config):
if not config.api_key:
if _is_nvidia_hosted(self.config):
if not self.config.api_key:
raise RuntimeError(
"API key is required for hosted NVIDIA NIM. Either provide an API key or use a self-hosted NIM."
)
# elif self._config.api_key:
#
# we don't raise this warning because a user may have deployed their
# self-hosted NIM with an API key requirement.
#
# warnings.warn(
# "API key is not required for self-hosted NVIDIA NIM. "
# "Consider removing the api_key from the configuration."
# )
self._config = config
def get_api_key(self) -> str:
"""
@ -70,7 +60,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
:return: The NVIDIA API key
"""
return self._config.api_key.get_secret_value() if self._config.api_key else "NO KEY"
return self.config.api_key.get_secret_value() if self.config.api_key else "NO KEY"
def get_base_url(self) -> str:
"""
@ -78,7 +68,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
:return: The NVIDIA API base URL
"""
return f"{self._config.url}/v1" if self._config.append_api_version else self._config.url
return f"{self.config.url}/v1" if self.config.append_api_version else self.config.url
async def openai_embeddings(
self,