llama-stack-mirror/llama_stack/providers/utils/inference
Ashwin Bharambe 74e2976c1e feat(api)!: support passing extra_body to embeddings and vector_stores APIs
Applies the same pattern from #3777 to embeddings and vector_stores.create() endpoints.

Breaking change: Method signatures now accept a single params object with Pydantic extra="allow" instead of individual parameters. Provider-specific params can be passed via extra_body and accessed through params.model_extra.

Updated APIs: openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()
2025-10-11 16:50:13 -07:00
..
__init__.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
embedding_mixin.py feat(api)!: support passing extra_body to embeddings and vector_stores APIs 2025-10-11 16:50:13 -07:00
inference_store.py chore: fix/add logging categories (#3658) 2025-10-02 13:10:13 -07:00
litellm_openai_mixin.py feat(api)!: support passing extra_body to embeddings and vector_stores APIs 2025-10-11 16:50:13 -07:00
model_registry.py feat: use SecretStr for inference provider auth credentials (#3724) 2025-10-10 07:32:50 -07:00
openai_compat.py fix: Update watsonx.ai provider to use LiteLLM mixin and list all models (#3674) 2025-10-08 07:29:43 -04:00
openai_mixin.py feat(api)!: support passing extra_body to embeddings and vector_stores APIs 2025-10-11 16:50:13 -07:00
prompt_adapter.py chore: remove /v1/inference/completion and implementations (#3622) 2025-10-01 11:36:53 -04:00