chore!: BREAKING CHANGE: vector_db_id -> vector_store_id (#3923)

# What does this PR do?


## Test Plan
CI
vector_io tests will fail until next client sync

passed with
https://github.com/llamastack/llama-stack-client-python/pull/286 checked
out locally

src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -488,13 +488,13 @@ class ChatAgent(ShieldRunnerMixin):
 
         session_info = await self.storage.get_session_info(session_id)
         # if the session has a memory bank id, let the memory tool use it
-        if session_info and session_info.vector_db_id:
+        if session_info and session_info.vector_store_id:
             for tool_name in self.tool_name_to_args.keys():
                 if tool_name == MEMORY_QUERY_TOOL:
-                    if "vector_db_ids" not in self.tool_name_to_args[tool_name]:
-                        self.tool_name_to_args[tool_name]["vector_db_ids"] = [session_info.vector_db_id]
+                    if "vector_store_ids" not in self.tool_name_to_args[tool_name]:
+                        self.tool_name_to_args[tool_name]["vector_store_ids"] = [session_info.vector_store_id]
                     else:
-                        self.tool_name_to_args[tool_name]["vector_db_ids"].append(session_info.vector_db_id)
+                        self.tool_name_to_args[tool_name]["vector_store_ids"].append(session_info.vector_store_id)
 
         output_attachments = []
 

src/llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -22,7 +22,7 @@ log = get_logger(name=__name__, category="agents::meta_reference")
 
 class AgentSessionInfo(Session):
     # TODO: is this used anywhere?
-    vector_db_id: str | None = None
+    vector_store_id: str | None = None
     started_at: datetime
     owner: User | None = None
     identifier: str | None = None
@@ -93,12 +93,12 @@ class AgentPersistence:
 
         return session_info
 
-    async def add_vector_db_to_session(self, session_id: str, vector_db_id: str):
+    async def add_vector_db_to_session(self, session_id: str, vector_store_id: str):
         session_info = await self.get_session_if_accessible(session_id)
         if session_info is None:
             raise SessionNotFoundError(session_id)
 
-        session_info.vector_db_id = vector_db_id
+        session_info.vector_store_id = vector_store_id
         await self.kvstore.set(
             key=f"session:{self.agent_id}:{session_id}",
             value=session_info.model_dump_json(),

src/llama_stack/providers/inline/tool_runtime/rag/memory.py

@@ -119,7 +119,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
     async def insert(
         self,
         documents: list[RAGDocument],
-        vector_db_id: str,
+        vector_store_id: str,
         chunk_size_in_tokens: int = 512,
     ) -> None:
         if not documents:
@@ -158,14 +158,14 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
 
                 try:
                     await self.vector_io_api.openai_attach_file_to_vector_store(
-                        vector_store_id=vector_db_id,
+                        vector_store_id=vector_store_id,
                         file_id=created_file.id,
                         attributes=doc.metadata,
                         chunking_strategy=chunking_strategy,
                     )
                 except Exception as e:
                     log.error(
-                        f"Failed to attach file {created_file.id} to vector store {vector_db_id} for document {doc.document_id}: {e}"
+                        f"Failed to attach file {created_file.id} to vector store {vector_store_id} for document {doc.document_id}: {e}"
                     )
                     continue
 
@@ -176,10 +176,10 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
     async def query(
         self,
         content: InterleavedContent,
-        vector_db_ids: list[str],
+        vector_store_ids: list[str],
         query_config: RAGQueryConfig | None = None,
     ) -> RAGQueryResult:
-        if not vector_db_ids:
+        if not vector_store_ids:
             raise ValueError(
                 "No vector DBs were provided to the knowledge search tool. Please provide at least one vector DB ID."
             )
@@ -192,7 +192,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
         )
         tasks = [
             self.vector_io_api.query_chunks(
-                vector_db_id=vector_db_id,
+                vector_store_id=vector_store_id,
                 query=query,
                 params={
                     "mode": query_config.mode,
@@ -201,18 +201,18 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
                     "ranker": query_config.ranker,
                 },
             )
-            for vector_db_id in vector_db_ids
+            for vector_store_id in vector_store_ids
         ]
         results: list[QueryChunksResponse] = await asyncio.gather(*tasks)
 
         chunks = []
         scores = []
 
-        for vector_db_id, result in zip(vector_db_ids, results, strict=False):
+        for vector_store_id, result in zip(vector_store_ids, results, strict=False):
             for chunk, score in zip(result.chunks, result.scores, strict=False):
                 if not hasattr(chunk, "metadata") or chunk.metadata is None:
                     chunk.metadata = {}
-                chunk.metadata["vector_db_id"] = vector_db_id
+                chunk.metadata["vector_store_id"] = vector_store_id
 
                 chunks.append(chunk)
                 scores.append(score)
@@ -250,7 +250,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
             metadata_keys_to_exclude_from_context = [
                 "token_count",
                 "metadata_token_count",
-                "vector_db_id",
+                "vector_store_id",
             ]
             metadata_for_context = {}
             for k in chunk_metadata_keys_to_include_from_context:
@@ -275,7 +275,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
                 "document_ids": [c.document_id for c in chunks[: len(picked)]],
                 "chunks": [c.content for c in chunks[: len(picked)]],
                 "scores": scores[: len(picked)],
-                "vector_db_ids": [c.metadata["vector_db_id"] for c in chunks[: len(picked)]],
+                "vector_store_ids": [c.metadata["vector_store_id"] for c in chunks[: len(picked)]],
             },
         )
 
@@ -309,7 +309,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
         )
 
     async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult:
-        vector_db_ids = kwargs.get("vector_db_ids", [])
+        vector_store_ids = kwargs.get("vector_store_ids", [])
         query_config = kwargs.get("query_config")
         if query_config:
             query_config = TypeAdapter(RAGQueryConfig).validate_python(query_config)
@@ -319,7 +319,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
         query = kwargs["query"]
         result = await self.query(
             content=query,
-            vector_db_ids=vector_db_ids,
+            vector_store_ids=vector_store_ids,
             query_config=query_config,
         )
 

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

@@ -248,19 +248,19 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoco
         del self.cache[vector_store_id]
         await self.kvstore.delete(f"{VECTOR_DBS_PREFIX}{vector_store_id}")
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = self.cache.get(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = self.cache.get(vector_store_id)
         if index is None:
-            raise ValueError(f"Vector DB {vector_db_id} not found. found: {self.cache.keys()}")
+            raise ValueError(f"Vector DB {vector_store_id} not found. found: {self.cache.keys()}")
 
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = self.cache.get(vector_db_id)
+        index = self.cache.get(vector_store_id)
         if index is None:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         return await index.query_chunks(query, params)
 

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

@@ -447,20 +447,20 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresPro
         await self.cache[vector_store_id].index.delete()
         del self.cache[vector_store_id]
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
         # The VectorStoreWithIndex helper is expected to compute embeddings via the inference_api
         # and then call our index's add_chunks.
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: Any, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: Any, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
         return await index.query_chunks(query, params)
 
     async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:

src/llama_stack/providers/registry/vector_io.py

@@ -163,14 +163,14 @@ The SQLite-vec provider supports three search modes:
 Example with hybrid search:
 ```python
 response = await vector_io.query_chunks(
-    vector_db_id="my_db",
+    vector_store_id="my_db",
     query="your query here",
     params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
 )
 
 # Using RRF ranker
 response = await vector_io.query_chunks(
-    vector_db_id="my_db",
+    vector_store_id="my_db",
     query="your query here",
     params={
         "mode": "hybrid",
@@ -182,7 +182,7 @@ response = await vector_io.query_chunks(
 
 # Using weighted ranker
 response = await vector_io.query_chunks(
-    vector_db_id="my_db",
+    vector_store_id="my_db",
     query="your query here",
     params={
         "mode": "hybrid",
@@ -196,7 +196,7 @@ response = await vector_io.query_chunks(
 Example with explicit vector search:
 ```python
 response = await vector_io.query_chunks(
-    vector_db_id="my_db",
+    vector_store_id="my_db",
     query="your query here",
     params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
 )
@@ -205,7 +205,7 @@ response = await vector_io.query_chunks(
 Example with keyword search:
 ```python
 response = await vector_io.query_chunks(
-    vector_db_id="my_db",
+    vector_store_id="my_db",
     query="your query here",
     params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
 )

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

@@ -169,20 +169,20 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc
         await self.cache[vector_store_id].index.delete()
         del self.cache[vector_store_id]
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if index is None:
-            raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
+            raise ValueError(f"Vector DB {vector_store_id} not found in Chroma")
 
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
 
         if index is None:
-            raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
+            raise ValueError(f"Vector DB {vector_store_id} not found in Chroma")
 
         return await index.query_chunks(query, params)
 

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

@@ -348,19 +348,19 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc
             await self.cache[vector_store_id].index.delete()
             del self.cache[vector_store_id]
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
         return await index.query_chunks(query, params)
 
     async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:

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

@@ -399,14 +399,14 @@ class PGVectorVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProt
         assert self.kvstore is not None
         await self.kvstore.delete(key=f"{VECTOR_DBS_PREFIX}{vector_store_id}")
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         return await index.query_chunks(query, params)
 
     async def _get_and_cache_vector_store_index(self, vector_store_id: str) -> VectorStoreWithIndex:

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

@@ -222,19 +222,19 @@ class QdrantVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc
         self.cache[vector_store_id] = index
         return index
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         return await index.query_chunks(query, params)
 

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

@@ -366,19 +366,19 @@ class WeaviateVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, NeedsRequestProv
         self.cache[vector_store_id] = index
         return index
 
-    async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+    async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         await index.insert_chunks(chunks)
 
     async def query_chunks(
-        self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
-        index = await self._get_and_cache_vector_store_index(vector_db_id)
+        index = await self._get_and_cache_vector_store_index(vector_store_id)
         if not index:
-            raise VectorStoreNotFoundError(vector_db_id)
+            raise VectorStoreNotFoundError(vector_store_id)
 
         return await index.query_chunks(query, params)
 

src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py

@@ -333,7 +333,7 @@ class OpenAIVectorStoreMixin(ABC):
     @abstractmethod
     async def insert_chunks(
         self,
-        vector_db_id: str,
+        vector_store_id: str,
         chunks: list[Chunk],
         ttl_seconds: int | None = None,
     ) -> None:
@@ -342,7 +342,7 @@ class OpenAIVectorStoreMixin(ABC):
 
     @abstractmethod
     async def query_chunks(
-        self, vector_db_id: str, query: Any, params: dict[str, Any] | None = None
+        self, vector_store_id: str, query: Any, params: dict[str, Any] | None = None
     ) -> QueryChunksResponse:
         """Query chunks from a vector database (provider-specific implementation)."""
         pass
@@ -609,7 +609,7 @@ class OpenAIVectorStoreMixin(ABC):
             # TODO: Add support for ranking_options.ranker
 
             response = await self.query_chunks(
-                vector_db_id=vector_store_id,
+                vector_store_id=vector_store_id,
                 query=search_query,
                 params=params,
             )
@@ -803,7 +803,7 @@ class OpenAIVectorStoreMixin(ABC):
                 )
             else:
                 await self.insert_chunks(
-                    vector_db_id=vector_store_id,
+                    vector_store_id=vector_store_id,
                     chunks=chunks,
                 )
                 vector_store_file_object.status = "completed"