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
|
@ -9,8 +9,6 @@ from llama_stack.providers.remote.inference.groq.config import GroqConfig
|
|||
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
|
||||
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
||||
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
|
||||
class GroqInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
||||
_config: GroqConfig
|
||||
|
@ -18,7 +16,6 @@ class GroqInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
|||
def __init__(self, config: GroqConfig):
|
||||
LiteLLMOpenAIMixin.__init__(
|
||||
self,
|
||||
model_entries=MODEL_ENTRIES,
|
||||
litellm_provider_name="groq",
|
||||
api_key_from_config=config.api_key,
|
||||
provider_data_api_key_field="groq_api_key",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue