feat: configure vector-io provider with an embedding model

Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>

docs/_static/llama-stack-spec.html

@@ -16306,15 +16306,15 @@
                     },
                     "embedding_model": {
                         "type": "string",
-                        "description": "The embedding model to use."
+                        "description": "The embedding model to use (optional if provider has defaults)."
                     },
                     "embedding_dimension": {
                         "type": "integer",
-                        "description": "The dimension of the embedding model."
+                        "description": "The dimension of the embedding model (optional if provider has defaults)."
                     },
                     "provider_id": {
                         "type": "string",
-                        "description": "The identifier of the provider."
+                        "description": "The identifier of the provider (can provide embedding defaults)."
                     },
                     "vector_db_name": {
                         "type": "string",
@@ -16327,8 +16327,7 @@
                 },
                 "additionalProperties": false,
                 "required": [
-                    "vector_db_id",
+                    "vector_db_id"
-                    "embedding_model"
                 ],
                 "title": "RegisterVectorDbRequest"
             },

docs/_static/llama-stack-spec.yaml

@@ -12114,13 +12114,16 @@ components:
             The identifier of the vector database to register.
         embedding_model:
           type: string
-          description: The embedding model to use.
+          description: >-
+            The embedding model to use (optional if provider has defaults).
         embedding_dimension:
           type: integer
-          description: The dimension of the embedding model.
+          description: >-
+            The dimension of the embedding model (optional if provider has defaults).
         provider_id:
           type: string
-          description: The identifier of the provider.
+          description: >-
+            The identifier of the provider (can provide embedding defaults).
         vector_db_name:
           type: string
           description: The name of the vector database.
@@ -12131,7 +12134,6 @@ components:
       additionalProperties: false
       required:
         - vector_db_id
-        - embedding_model
       title: RegisterVectorDbRequest
     ResumeAgentTurnRequest:
       type: object

docs/source/providers/vector_io/inline_chromadb.md

@@ -43,6 +43,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/inline_faiss.md

@@ -38,6 +38,7 @@ more details about Faiss in general.
 | 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` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/inline_meta-reference.md

@@ -9,6 +9,7 @@ Meta's reference implementation of a vector database.
 | 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` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/inline_milvus.md

@@ -13,6 +13,7 @@ Please refer to the remote provider documentation.
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/inline_sqlite-vec.md

@@ -207,6 +207,7 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined | Path to the SQLite database file |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/inline_sqlite_vec.md

@@ -12,6 +12,7 @@ Please refer to the sqlite-vec provider documentation.
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined | Path to the SQLite database file |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/remote_chromadb.md

@@ -42,6 +42,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
 |-------|------|----------|---------|-------------|
 | `url` | `str \| None` | No | PydanticUndefined |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/remote_milvus.md

@@ -115,6 +115,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
 | `token` | `str \| None` | No | PydanticUndefined | The token of the Milvus server |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 | `config` | `dict` | No | {} | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |
 
 > **Note**: This configuration class accepts additional fields beyond those listed above. You can pass any additional configuration options that will be forwarded to the underlying provider.

docs/source/providers/vector_io/remote_pgvector.md

@@ -41,6 +41,7 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
 | `user` | `str \| None` | No | postgres |  |
 | `password` | `str \| None` | No | mysecretpassword |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/remote_qdrant.md

@@ -21,6 +21,7 @@ Please refer to the inline provider documentation.
 | `timeout` | `int \| None` | No |  |  |
 | `host` | `str \| None` | No |  |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

docs/source/providers/vector_io/remote_weaviate.md

@@ -40,6 +40,7 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
 | `weaviate_api_key` | `str \| None` | No |  | The API key for the Weaviate instance |
 | `weaviate_cluster_url` | `str \| None` | No | localhost:8080 | The URL of the Weaviate cluster |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
+| `embedding` | `utils.vector_io.embedding_config.EmbeddingConfig \| None` | No |  | Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults. |
 
 ## Sample Configuration
 

llama_stack/apis/vector_dbs/vector_dbs.py

@@ -41,14 +41,15 @@ class VectorDBInput(BaseModel):
     """Input parameters for creating or configuring a vector database.
 
     :param vector_db_id: Unique identifier for the vector database
-    :param embedding_model: Name of the embedding model to use for vector generation
+    :param embedding_model: Name of the embedding model to use for vector generation (optional if provider has defaults)
-    :param embedding_dimension: Dimension of the embedding vectors
+    :param embedding_dimension: Dimension of the embedding vectors (optional if provider has defaults)
+    :param provider_id: Provider to use for this vector database (can inherit embedding defaults)
     :param provider_vector_db_id: (Optional) Provider-specific identifier for the vector database
     """
 
     vector_db_id: str
-    embedding_model: str
+    embedding_model: str | None = None
-    embedding_dimension: int
+    embedding_dimension: int | None = None
     provider_id: str | None = None
     provider_vector_db_id: str | None = None
 
@@ -89,8 +90,8 @@ class VectorDBs(Protocol):
     async def register_vector_db(
         self,
         vector_db_id: str,
-        embedding_model: str,
+        embedding_model: str | None = None,
-        embedding_dimension: int | None = 384,
+        embedding_dimension: int | None = None,
         provider_id: str | None = None,
         vector_db_name: str | None = None,
         provider_vector_db_id: str | None = None,
@@ -98,9 +99,9 @@ class VectorDBs(Protocol):
         """Register a vector database.
 
         :param vector_db_id: The identifier of the vector database to register.
-        :param embedding_model: The embedding model to use.
+        :param embedding_model: The embedding model to use (optional if provider has defaults).
-        :param embedding_dimension: The dimension of the embedding model.
+        :param embedding_dimension: The dimension of the embedding model (optional if provider has defaults).
-        :param provider_id: The identifier of the provider.
+        :param provider_id: The identifier of the provider (can provide embedding defaults).
         :param vector_db_name: The name of the vector database.
         :param provider_vector_db_id: The identifier of the vector database in the provider.
         :returns: A VectorDB.

llama_stack/core/routers/vector_io.py

@@ -79,13 +79,23 @@ class VectorIORouter(VectorIO):
     async def register_vector_db(
         self,
         vector_db_id: str,
-        embedding_model: str,
+        embedding_model: str | None = None,
-        embedding_dimension: int | None = 384,
+        embedding_dimension: int | None = None,
         provider_id: str | None = None,
         vector_db_name: str | None = None,
         provider_vector_db_id: str | None = None,
     ) -> None:
-        logger.debug(f"VectorIORouter.register_vector_db: {vector_db_id}, {embedding_model}")
+        logger.debug(
+            f"VectorIORouter.register_vector_db: {vector_db_id}, embedding_model={embedding_model}, provider_id={provider_id}"
+        )
+
+        # If embedding model/dimension not provided, they will be applied by the provider
+        # from its embedding configuration during register_vector_db call
+        if embedding_model is None and embedding_dimension is None:
+            # Use fallback defaults if no provider defaults are available
+            embedding_model = embedding_model or "all-MiniLM-L6-v2"
+            embedding_dimension = embedding_dimension or 384
+
         await self.routing_table.register_vector_db(
             vector_db_id,
             embedding_model,

llama_stack/providers/inline/vector_io/chroma/config.py

@@ -9,6 +9,7 @@ from typing import Any
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -16,6 +17,10 @@ from llama_stack.schema_utils import json_schema_type
 class ChromaVectorIOConfig(BaseModel):
     db_path: str
     kvstore: KVStoreConfig = Field(description="Config for KV store backend")
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(
@@ -27,4 +32,9 @@ class ChromaVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="chroma_inline_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.CHROMA_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/inline/vector_io/faiss/config.py

@@ -6,18 +6,23 @@
 
 from typing import Any
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
 @json_schema_type
 class FaissVectorIOConfig(BaseModel):
     kvstore: KVStoreConfig
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
@@ -25,5 +30,10 @@ class FaissVectorIOConfig(BaseModel):
             "kvstore": SqliteKVStoreConfig.sample_run_config(
                 __distro_dir__=__distro_dir__,
                 db_name="faiss_store.db",
-            )
+            ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.FAISS_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -35,6 +35,7 @@ from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIV
 from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
+    apply_provider_embedding_defaults,
 )
 
 from .config import FaissVectorIOConfig
@@ -237,6 +238,9 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
         self,
         vector_db: VectorDB,
     ) -> None:
+        # Apply provider-level embedding defaults if configured
+        vector_db = apply_provider_embedding_defaults(vector_db, self.config.embedding)
+
         assert self.kvstore is not None
 
         key = f"{VECTOR_DBS_PREFIX}{vector_db.identifier}"

llama_stack/providers/inline/vector_io/milvus/config.py

@@ -12,6 +12,7 @@ from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -20,6 +21,10 @@ class MilvusVectorIOConfig(BaseModel):
     db_path: str
     kvstore: KVStoreConfig = Field(description="Config for KV store backend (SQLite only for now)")
     consistency_level: str = Field(description="The consistency level of the Milvus server", default="Strong")
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
@@ -29,4 +34,9 @@ class MilvusVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="milvus_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.MILVUS_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/inline/vector_io/sqlite_vec/config.py

@@ -12,11 +12,18 @@ from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
+from llama_stack.schema_utils import json_schema_type
 
 
+@json_schema_type
 class SQLiteVectorIOConfig(BaseModel):
     db_path: str = Field(description="Path to the SQLite database file")
     kvstore: KVStoreConfig = Field(description="Config for KV store backend (SQLite only for now)")
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
@@ -26,4 +33,9 @@ class SQLiteVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="sqlite_vec_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.SQLITE_VEC_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/remote/vector_io/chroma/config.py

@@ -9,6 +9,7 @@ from typing import Any
 from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -16,6 +17,10 @@ from llama_stack.schema_utils import json_schema_type
 class ChromaVectorIOConfig(BaseModel):
     url: str | None
     kvstore: KVStoreConfig = Field(description="Config for KV store backend")
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str, url: str = "${env.CHROMADB_URL}", **kwargs: Any) -> dict[str, Any]:
@@ -25,4 +30,9 @@ class ChromaVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="chroma_remote_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.CHROMA_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/remote/vector_io/milvus/config.py

@@ -9,6 +9,7 @@ from typing import Any
 from pydantic import BaseModel, ConfigDict, Field
 
 from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -18,6 +19,10 @@ class MilvusVectorIOConfig(BaseModel):
     token: str | None = Field(description="The token of the Milvus server")
     consistency_level: str = Field(description="The consistency level of the Milvus server", default="Strong")
     kvstore: KVStoreConfig = Field(description="Config for KV store backend")
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     # This configuration allows additional fields to be passed through to the underlying Milvus client.
     # See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general.
@@ -32,4 +37,9 @@ class MilvusVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="milvus_remote_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.MILVUS_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -29,6 +29,7 @@ from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIV
 from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
+    apply_provider_embedding_defaults,
 )
 from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collection_name
 
@@ -305,6 +306,9 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
         self,
         vector_db: VectorDB,
     ) -> None:
+        # Apply provider-level embedding defaults if configured
+        vector_db = apply_provider_embedding_defaults(vector_db, self.config.embedding)
+
         if isinstance(self.config, RemoteMilvusVectorIOConfig):
             consistency_level = self.config.consistency_level
         else:

llama_stack/providers/remote/vector_io/pgvector/config.py

@@ -12,6 +12,7 @@ from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -23,6 +24,10 @@ class PGVectorVectorIOConfig(BaseModel):
     user: str | None = Field(default="postgres")
     password: str | None = Field(default="mysecretpassword")
     kvstore: KVStoreConfig | None = Field(description="Config for KV store backend (SQLite only for now)", default=None)
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(
@@ -45,4 +50,9 @@ class PGVectorVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="pgvector_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.PGVECTOR_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -29,6 +29,7 @@ from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIV
 from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
+    apply_provider_embedding_defaults,
 )
 
 from .config import PGVectorVectorIOConfig
@@ -222,6 +223,9 @@ class PGVectorVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoco
             log.info("Connection to PGVector database server closed")
 
     async def register_vector_db(self, vector_db: VectorDB) -> None:
+        # Apply provider-level embedding defaults if configured
+        vector_db = apply_provider_embedding_defaults(vector_db, self.config.embedding)
+
         # Persist vector DB metadata in the KV store
         assert self.kvstore is not None
         # Upsert model metadata in Postgres

llama_stack/providers/remote/vector_io/qdrant/config.py

@@ -6,12 +6,13 @@
 
 from typing import Any
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -28,6 +29,10 @@ class QdrantVectorIOConfig(BaseModel):
     timeout: int | None = None
     host: str | None = None
     kvstore: KVStoreConfig
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
@@ -37,4 +42,10 @@ class QdrantVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="qdrant_registry.db",
             ),
+            "api_key": "${env.QDRANT_API_KEY}",
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.QDRANT_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/remote/vector_io/weaviate/config.py

@@ -12,6 +12,7 @@ from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -21,6 +22,13 @@ class WeaviateVectorIOConfig(BaseModel):
     weaviate_cluster_url: str | None = Field(description="The URL of the Weaviate cluster", default="localhost:8080")
     kvstore: KVStoreConfig | None = Field(description="Config for KV store backend (SQLite only for now)", default=None)
 
+
+@json_schema_type
+class WeaviateVectorIOConfig(BaseModel):
+    embedding: EmbeddingConfig | None = Field(
+        default=None,
+        description="Default embedding configuration for this provider. When specified, vector databases created with this provider will use these embedding settings as defaults.",
+    )
     @classmethod
     def sample_run_config(
         cls,
@@ -34,4 +42,9 @@ class WeaviateVectorIOConfig(BaseModel):
                 __distro_dir__=__distro_dir__,
                 db_name="weaviate_registry.db",
             ),
+            # Optional: Configure default embedding model for this provider
+            # "embedding": {
+            #     "model": "${env.WEAVIATE_EMBEDDING_MODEL:=all-MiniLM-L6-v2}",
+            #     "dimensions": 384
+            # },
         }

llama_stack/providers/utils/memory/vector_store.py

@@ -31,6 +31,8 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )
 from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
+from llama_stack.providers.utils.vector_io.chunk_utils import generate_chunk_id
+from llama_stack.providers.utils.vector_io.embedding_config import EmbeddingConfig
 
 log = logging.getLogger(__name__)
 
@@ -39,6 +41,41 @@ RERANKER_TYPE_RRF = "rrf"
 RERANKER_TYPE_WEIGHTED = "weighted"
 
 
+def apply_provider_embedding_defaults(
+    vector_db: VectorDB, provider_embedding_config: EmbeddingConfig | None
+) -> VectorDB:
+    """Apply provider-level embedding defaults to a VectorDB if not already specified.
+
+    This allows providers to specify default embedding models for use-case specific
+    vector stores, reducing the need for app developers to know embedding details.
+
+    Args:
+        vector_db: The VectorDB to potentially modify
+        provider_embedding_config: The provider's default embedding configuration
+
+    Returns:
+        The VectorDB with embedding defaults applied if needed
+    """
+    if provider_embedding_config is None:
+        return vector_db
+
+    # Create a copy to avoid modifying the original
+    db_dict = vector_db.model_dump()
+
+    # Apply embedding model default if not specified
+    if not db_dict.get("embedding_model") and provider_embedding_config.model:
+        db_dict["embedding_model"] = provider_embedding_config.model
+
+    # Apply embedding dimension default if not specified
+    if not db_dict.get("embedding_dimension") and provider_embedding_config.dimensions:
+        db_dict["embedding_dimension"] = provider_embedding_config.dimensions
+    elif not db_dict.get("embedding_dimension"):
+        # Fallback to default dimension if still not specified
+        db_dict["embedding_dimension"] = provider_embedding_config.get_dimensions_or_default()
+
+    return VectorDB.model_validate(db_dict)
+
+
 def parse_pdf(data: bytes) -> str:
     # For PDF and DOC/DOCX files, we can't reliably convert to string
     pdf_bytes = io.BytesIO(data)

llama_stack/providers/utils/vector_io/embedding_config.py

@@ -0,0 +1,36 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from pydantic import BaseModel, Field
+
+from llama_stack.schema_utils import json_schema_type
+
+
+@json_schema_type
+class EmbeddingConfig(BaseModel):
+    """Configuration for embedding model used by vector-io providers.
+
+    This allows providers to specify default embedding models for use-case specific
+    vector stores, reducing the need for app developers to know embedding details.
+
+    Example usage in provider config:
+    ```yaml
+    vector_io:
+      - provider_id: question-answer
+        provider_type: remote::pgvector
+        config:
+          embedding:
+            model: prod/question-answer-embedder
+            dimensions: 384
+    ```
+    """
+
+    model: str = Field(description="The embedding model identifier to use")
+    dimensions: int | None = Field(default=None, description="The embedding dimensions (optional, can be inferred)")
+
+    def get_dimensions_or_default(self, default: int = 384) -> int:
+        """Get dimensions with fallback to default if not specified."""
+        return self.dimensions if self.dimensions is not None else default