feat(api): Add vector store file batches api (#3642)

# What does this PR do?

Add Open AI Compatible vector store file batches api. This functionality
is needed to attach many files to a vector store as a batch.
#3533

API Stubs have been merged
#3615
Adds persistence for file batches as discussed in diff
#3544
(Used claude code for generation and reviewed by me)


## Test Plan
1. Unit tests pass
2. Also verified the cc-vec integration with LLamaStackClient works with
the file batches api. https://github.com/raghotham/cc-vec
2. Integration tests pass

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

@@ -200,12 +200,10 @@ async def query_hybrid(
 
 class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
     def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
-        self.files_api = files_api
         self.cache: dict[str, VectorDBWithIndex] = {}
-        self.kvstore: KVStore | None = None
-        self.openai_vector_stores: 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

@@ -410,12 +410,10 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
     """
 
     def __init__(self, config, inference_api: Inference, files_api: Files | None) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
-        self.files_api = files_api
         self.cache: dict[str, VectorDBWithIndex] = {}
-        self.openai_vector_stores: dict[str, dict[str, Any]] = {}
-        self.kvstore: KVStore | None = None
 
     async def initialize(self) -> None:
         self.kvstore = await kvstore_impl(self.config.kvstore)

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

@@ -140,14 +140,13 @@ def __init__(
         inference_api: Api.inference,
         files_api: Files | None,
     ) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         log.info(f"Initializing ChromaVectorIOAdapter with url: {config}")
         self.config = config
         self.inference_api = inference_api
         self.client = None
         self.cache = {}
-        self.kvstore: KVStore | None = None
         self.vector_db_store = None
-        self.files_api = files_api
 
     async def initialize(self) -> None:
         self.kvstore = await kvstore_impl(self.config.kvstore)

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

@@ -309,14 +309,12 @@ def __init__(
         inference_api: Inference,
         files_api: Files | None,
     ) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.cache = {}
         self.client = None
         self.inference_api = inference_api
-        self.files_api = files_api
-        self.kvstore: KVStore | None = None
         self.vector_db_store = None
-        self.openai_vector_stores: 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

@@ -345,14 +345,12 @@ def __init__(
         inference_api: Api.inference,
         files_api: Files | None = None,
     ) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
         self.conn = None
         self.cache = {}
-        self.files_api = files_api
-        self.kvstore: KVStore | None = None
         self.vector_db_store = None
-        self.openai_vector_stores: 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

@@ -27,7 +27,7 @@
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
-from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
+from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
 from llama_stack.providers.utils.memory.vector_store import (
     ChunkForDeletion,
@@ -162,14 +162,12 @@ def __init__(
         inference_api: Api.inference,
         files_api: Files | None = None,
     ) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.client: AsyncQdrantClient = None
         self.cache = {}
         self.inference_api = inference_api
-        self.files_api = files_api
         self.vector_db_store = None
-        self.kvstore: KVStore | None = None
-        self.openai_vector_stores: dict[str, dict[str, Any]] = {}
         self._qdrant_lock = asyncio.Lock()
 
     async def initialize(self) -> None:

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

@@ -284,14 +284,12 @@ def __init__(
         inference_api: Api.inference,
         files_api: Files | None,
     ) -> None:
+        super().__init__(files_api=files_api, kvstore=None)
         self.config = config
         self.inference_api = inference_api
         self.client_cache = {}
         self.cache = {}
-        self.files_api = files_api
-        self.kvstore: KVStore | None = None
         self.vector_db_store = None
-        self.openai_vector_stores: dict[str, dict[str, Any]] = {}
         self.metadata_collection_name = "openai_vector_stores_metadata"
 
     def _get_client(self) -> weaviate.WeaviateClient: