phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 12:06:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove experimental from rerank models doc

Browse source
This commit is contained in:
Jiayi 2025-10-17 14:51:17 -07:00
parent 51c923f096
commit ad52849072
9 changed files with 13 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -48,6 +48,7 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
- overwrite_completion_id: If True, overwrites the 'id' field in OpenAI responses
- download_images: If True, downloads images and converts to base64 for providers that require it
- embedding_model_metadata: A dictionary mapping model IDs to their embedding metadata
- rerank_model_list: A list of model IDs for rerank models
- provider_data_api_key_field: Optional field name in provider data to look for API key
- list_provider_model_ids: Method to list available models from the provider
- get_extra_client_params: Method to provide extra parameters to the AsyncOpenAI client