phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin

Browse source 
- 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
This commit is contained in:
Matthew Farrellee 2025-09-25 04:56:54 -04:00
parent a50b63906c
commit 466ef6f490
43 changed files with 370 additions and 1016 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -40,7 +40,7 @@ from llama_stack.apis.inference import (
)
from llama_stack.core.request_headers import NeedsRequestProviderData
from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry
from llama_stack.providers.utils.inference.openai_compat import (
b64_encode_openai_embeddings_response,
convert_message_to_openai_dict_new,
@ -67,10 +67,10 @@ class LiteLLMOpenAIMixin(
# when calling litellm.
def __init__(
self,
model_entries,
litellm_provider_name: str,
api_key_from_config: str | None,
provider_data_api_key_field: str,
model_entries: list[ProviderModelEntry] | None = None,
openai_compat_api_base: str | None = None,
download_images: bool = False,
json_schema_strict: bool = True,
@ -86,7 +86,7 @@ class LiteLLMOpenAIMixin(
:param download_images: Whether to download images and convert to base64 for message conversion.
:param json_schema_strict: Whether to use strict mode for JSON schema validation.
"""
ModelRegistryHelper.__init__(self, model_entries)
ModelRegistryHelper.__init__(self, model_entries=model_entries)
self.litellm_provider_name = litellm_provider_name
self.api_key_from_config = api_key_from_config