Merge fa7144163e into 2f58d87c22

docs/_static/llama-stack-spec.html

@@ -17091,14 +17091,14 @@
                         "type": "string",
                         "description": "The embedding model to use."
                     },
-                    "embedding_dimension": {
-                        "type": "integer",
-                        "description": "The dimension of the embedding model."
-                    },
                     "provider_id": {
                         "type": "string",
                         "description": "The identifier of the provider."
                     },
+                    "embedding_dimension": {
+                        "type": "integer",
+                        "description": "The dimension of the embedding model."
+                    },
                     "vector_db_name": {
                         "type": "string",
                         "description": "The name of the vector database."
@@ -17111,7 +17111,8 @@
                 "additionalProperties": false,
                 "required": [
                     "vector_db_id",
-                    "embedding_model"
+                    "embedding_model",
+                    "provider_id"
                 ],
                 "title": "RegisterVectorDbRequest"
             },

docs/_static/llama-stack-spec.yaml

@@ -12708,12 +12708,12 @@ components:
         embedding_model:
           type: string
           description: The embedding model to use.
-        embedding_dimension:
-          type: integer
-          description: The dimension of the embedding model.
         provider_id:
           type: string
           description: The identifier of the provider.
+        embedding_dimension:
+          type: integer
+          description: The dimension of the embedding model.
         vector_db_name:
           type: string
           description: The name of the vector database.
@@ -12725,6 +12725,7 @@ components:
       required:
         - vector_db_id
         - embedding_model
+        - provider_id
       title: RegisterVectorDbRequest
     RerankRequest:
       type: object

llama_stack/apis/vector_dbs/vector_dbs.py

@@ -90,8 +90,8 @@ class VectorDBs(Protocol):
         self,
         vector_db_id: str,
         embedding_model: str,
+        provider_id: str,
         embedding_dimension: int | None = 384,
-        provider_id: str | None = None,
         vector_db_name: str | None = None,
         provider_vector_db_id: str | None = None,
     ) -> VectorDB:

llama_stack/core/routing_tables/vector_dbs.py

@@ -47,20 +47,11 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
         self,
         vector_db_id: str,
         embedding_model: str,
+        provider_id: str,
         embedding_dimension: int | None = 384,
-        provider_id: str | None = None,
         provider_vector_db_id: str | None = None,
         vector_db_name: str | None = None,
     ) -> VectorDB:
-        if provider_id is None:
-            if len(self.impls_by_provider_id) > 0:
-                provider_id = list(self.impls_by_provider_id.keys())[0]
-                if len(self.impls_by_provider_id) > 1:
-                    logger.warning(
-                        f"No provider specified and multiple providers available. Arbitrarily selected the first provider {provider_id}."
-                    )
-            else:
-                raise ValueError("No provider available. Please configure a vector_io provider.")
         model = await lookup_model(self, embedding_model)
         if model is None:
             raise ModelNotFoundError(embedding_model)