mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)
# What does this PR do? - remove auto-download of ollama embedding models - add embedding model metadata to dynamic listing w/ unit test - add support and tests for allowed_models - removed inference provider models.py files where dynamic listing is enabled - store embedding metadata in embedding_model_metadata field on inference providers - make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin - make OpenAIMixin a ModelRegistryHelper - skip base64 embedding test for remote::ollama, always returns floats - only use OpenAI client for ollama model listing - remove unused build_model_entry function - remove unused get_huggingface_repo function ## Test Plan ci w/ new tests
This commit is contained in:
parent
a50b63906c
commit
b67aef2fc4
43 changed files with 368 additions and 1015 deletions
|
@ -14,7 +14,6 @@ from llama_stack.apis.datasets import Datasets
|
|||
from llama_stack.apis.inference import Inference
|
||||
from llama_stack.apis.scoring import Scoring, ScoringResult
|
||||
from llama_stack.providers.datatypes import BenchmarksProtocolPrivate
|
||||
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
|
||||
from .....apis.common.job_types import Job, JobStatus
|
||||
|
@ -45,7 +44,7 @@ class NVIDIAEvalImpl(
|
|||
self.inference_api = inference_api
|
||||
self.agents_api = agents_api
|
||||
|
||||
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
|
||||
ModelRegistryHelper.__init__(self)
|
||||
|
||||
async def initialize(self) -> None: ...
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue