feat(api): Add vector store file batches api

Author: slekkala1

llama_stack/core/routing_tables/vector_dbs.py

@@ -245,3 +245,65 @@ async def openai_delete_vector_store_file(
             vector_store_id=vector_store_id,
             file_id=file_id,
         )
+
+    async def openai_create_vector_store_file_batch(
+        self,
+        vector_store_id: str,
+        file_ids: list[str],
+        attributes: dict[str, Any] | None = None,
+        chunking_strategy: Any | None = None,
+    ):
+        await self.assert_action_allowed("update", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_create_vector_store_file_batch(
+            vector_store_id=vector_store_id,
+            file_ids=file_ids,
+            attributes=attributes,
+            chunking_strategy=chunking_strategy,
+        )
+
+    async def openai_retrieve_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+    ):
+        await self.assert_action_allowed("read", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_retrieve_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+        )
+
+    async def openai_list_files_in_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+        after: str | None = None,
+        before: str | None = None,
+        filter: str | None = None,
+        limit: int | None = 20,
+        order: str | None = "desc",
+    ):
+        await self.assert_action_allowed("read", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_list_files_in_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+            after=after,
+            before=before,
+            filter=filter,
+            limit=limit,
+            order=order,
+        )
+
+    async def openai_cancel_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+    ):
+        await self.assert_action_allowed("update", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_cancel_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+        )

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

@@ -206,6 +206,7 @@ def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_
         self.cache: dict[str, VectorDBWithIndex] = {}
         self.kvstore: KVStore | None = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
 
     async def initialize(self) -> None:
         self.kvstore = await kvstore_impl(self.config.kvstore)

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

@@ -415,6 +415,7 @@ def __init__(self, config, inference_api: Inference, files_api: Files | None) ->
         self.files_api = files_api
         self.cache: dict[str, VectorDBWithIndex] = {}
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
         self.kvstore: KVStore | None = None
 
     async def initialize(self) -> None:

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

@@ -166,6 +166,7 @@ async def initialize(self) -> None:
             log.info(f"Connecting to Chroma local db at: {self.config.db_path}")
             self.client = chromadb.PersistentClient(path=self.config.db_path)
         self.openai_vector_stores = await self._load_openai_vector_stores()
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
 
     async def shutdown(self) -> None:
         pass

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

@@ -317,6 +317,7 @@ def __init__(
         self.kvstore: KVStore | None = None
         self.vector_db_store = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
         self.metadata_collection_name = "openai_vector_stores_metadata"
 
     async def initialize(self) -> None:

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

@@ -353,6 +353,7 @@ def __init__(
         self.kvstore: KVStore | None = None
         self.vector_db_store = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
         self.metadata_collection_name = "openai_vector_stores_metadata"
 
     async def initialize(self) -> None:

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

@@ -170,6 +170,7 @@ def __init__(
         self.vector_db_store = None
         self.kvstore: KVStore | None = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
         self._qdrant_lock = asyncio.Lock()
 
     async def initialize(self) -> None:

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

@@ -170,6 +170,7 @@ def __init__(
         self.kvstore: KVStore | None = None
         self.vector_db_store = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self.openai_file_batches: dict[str, dict[str, Any]] = {}
         self.metadata_collection_name = "openai_vector_stores_metadata"
 
     def _get_client(self) -> weaviate.Client: