mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 00:42:25 +00:00

skamenan7 474b50b422 Add configurable embedding models for vector IO providers

This change lets users configure default embedding models at the provider level instead of always relying on system defaults. Each vector store provider can now specify an embedding_model and optional embedding_dimension in their config.

Key features:
- Auto-dimension lookup for standard models from the registry
- Support for Matryoshka embeddings with custom dimensions
- Three-tier priority: explicit params > provider config > system fallback
- Full backward compatibility - existing setups work unchanged
- Comprehensive test coverage with 20 test cases

Updated all vector IO providers (FAISS, Chroma, Milvus, Qdrant, etc.) with the new config fields and added detailed documentation with examples.

Fixes #2729

2025-07-15 16:46:40 -04:00

1,021 B

Raw Blame History

inline::meta-reference

Description

Meta's reference implementation of a vector database.

Configuration

Field	Type	Required	Default	Description
`kvstore`	`utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig`	No	sqlite
`embedding_model`	`str \| None`	No		Optional default embedding model for this provider. If not specified, will use system default.
`embedding_dimension`	`int \| None`	No		Optional embedding dimension override. Only needed for models with variable dimensions (e.g., Matryoshka embeddings). If not specified, will auto-lookup from model registry.

Sample Configuration

kvstore:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db

Deprecation Notice

⚠️ Warning: Please use the inline::faiss provider instead.

1,021 B Raw Blame History