Merge branch 'main' into make-provider-model-id-non-optional

llama_stack/apis/tools/rag_tool.py

@@ -87,6 +87,20 @@ class RAGQueryGenerator(Enum):
     custom = "custom"
 
 
+@json_schema_type
+class RAGSearchMode(Enum):
+    """
+    Search modes for RAG query retrieval:
+    - VECTOR: Uses vector similarity search for semantic matching
+    - KEYWORD: Uses keyword-based search for exact matching
+    - HYBRID: Combines both vector and keyword search for better results
+    """
+
+    VECTOR = "vector"
+    KEYWORD = "keyword"
+    HYBRID = "hybrid"
+
+
 @json_schema_type
 class DefaultRAGQueryGeneratorConfig(BaseModel):
     type: Literal["default"] = "default"
@@ -128,7 +142,7 @@ class RAGQueryConfig(BaseModel):
     max_tokens_in_context: int = 4096
     max_chunks: int = 5
     chunk_template: str = "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
-    mode: str | None = None
+    mode: RAGSearchMode | None = RAGSearchMode.VECTOR
     ranker: Ranker | None = Field(default=None)  # Only used for hybrid mode
 
     @field_validator("chunk_template")

llama_stack/apis/vector_dbs/vector_dbs.py

@@ -19,6 +19,7 @@ class VectorDB(Resource):
 
     embedding_model: str
     embedding_dimension: int
+    vector_db_name: str | None = None
 
     @property
     def vector_db_id(self) -> str:
@@ -70,6 +71,7 @@ class VectorDBs(Protocol):
         embedding_model: 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:
         """Register a vector database.
@@ -78,6 +80,7 @@ class VectorDBs(Protocol):
         :param embedding_model: The embedding model to use.
         :param embedding_dimension: The dimension of the embedding model.
         :param provider_id: The identifier of the provider.
+        :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/apis/vector_io/vector_io.py

@@ -346,7 +346,6 @@ class VectorIO(Protocol):
         embedding_model: str | None = None,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
-        provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         """Creates a vector store.
 
@@ -358,7 +357,6 @@ class VectorIO(Protocol):
         :param embedding_model: The embedding model to use for this vector store.
         :param embedding_dimension: The dimension of the embedding vectors (default: 384).
         :param provider_id: The ID of the provider to use for this vector store.
-        :param provider_vector_db_id: The provider-specific vector database ID.
         :returns: A VectorStoreObject representing the created vector store.
         """
         ...