fix(vector_io): wire file_processors provider into vector store file insertion

src/llama_stack/providers/inline/vector_io/chroma/__init__.py

@@ -14,6 +14,6 @@
 async def get_provider_impl(config: ChromaVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.chroma.chroma import ChromaVectorIOAdapter
 
-    impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -16,6 +16,6 @@ async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
 
     assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"
 
-    impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -57,6 +57,7 @@ def _get_numpy() -> Any:
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     HealthResponse,
     HealthStatus,
@@ -345,8 +346,16 @@ async def query_hybrid(
 class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtocolPrivate):
     """Vector I/O adapter using FAISS for in-memory vector similarity search."""
 
-    def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+    def __init__(
+        self,
+        config: FaissVectorIOConfig,
+        inference_api: Inference,
+        files_api: Files | None,
+        file_processor_api: FileProcessors | None = None,
+    ) -> None:
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         self.config = config
         self.cache: dict[str, VectorStoreWithIndex] = {}
 

src/llama_stack/providers/inline/vector_io/milvus/__init__.py

@@ -14,6 +14,6 @@
 async def get_provider_impl(config: MilvusVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusVectorIOAdapter
 
-    impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

src/llama_stack/providers/inline/vector_io/qdrant/__init__.py

@@ -15,6 +15,6 @@ async def get_provider_impl(config: QdrantVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
 
     assert isinstance(config, QdrantVectorIOConfig), f"Unexpected config type: {type(config)}"
-    impl = QdrantVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = QdrantVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -15,6 +15,6 @@ async def get_provider_impl(config: SQLiteVectorIOConfig, deps: dict[Api, Any]):
     from .sqlite_vec import SQLiteVecVectorIOAdapter
 
     assert isinstance(config, SQLiteVectorIOConfig), f"Unexpected config type: {type(config)}"
-    impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -64,6 +64,7 @@ def _get_sqlite_vec() -> Any:
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Inference,
     InsertChunksRequest,
@@ -523,8 +524,16 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresPro
     and creates a cache of VectorStoreWithIndex instances (each wrapping a SQLiteVecIndex).
     """
 
-    def __init__(self, config, inference_api: Inference, files_api: Files | None) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+    def __init__(
+        self,
+        config,
+        inference_api: Inference,
+        files_api: Files | None,
+        file_processor_api: FileProcessors | None = None,
+    ) -> None:
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         self.config = config
         self.cache: dict[str, VectorStoreWithIndex] = {}
         self.vector_store_table = None

src/llama_stack/providers/registry/vector_io.py

@@ -31,7 +31,7 @@ def available_providers() -> list[ProviderSpec]:
             config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
             deprecation_warning="Please use the `inline::faiss` provider instead.",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="Meta's reference implementation of a vector database.",
         ),
         InlineProviderSpec(
@@ -41,7 +41,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.inline.vector_io.faiss",
             config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Faiss](https://github.com/facebookresearch/faiss) is an inline vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
@@ -94,7 +94,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.inline.vector_io.sqlite_vec",
             config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [SQLite-Vec](https://github.com/asg017/sqlite-vec) is an inline vector database provider for Llama Stack. It
 allows you to store and query vectors directly within an SQLite database.
@@ -302,7 +302,7 @@ def available_providers() -> list[ProviderSpec]:
             config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
             deprecation_warning="Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 Please refer to the sqlite-vec provider documentation.
 """,
@@ -315,7 +315,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.chroma",
             config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Chroma](https://www.trychroma.com/) is an inline and remote vector
 database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
@@ -357,7 +357,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.inline.vector_io.chroma",
             config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Chroma](https://www.trychroma.com/) is an inline and remote vector
 database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
@@ -401,7 +401,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.pgvector",
             config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [PGVector](https://github.com/pgvector/pgvector) is a remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
@@ -534,7 +534,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.weaviate",
             config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Weaviate](https://weaviate.io/) is a vector database provider for Llama Stack.
 It allows you to store and query vectors directly within a Weaviate database.
@@ -574,7 +574,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.inline.vector_io.qdrant",
             config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description=r"""
 [Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
@@ -627,7 +627,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.qdrant",
             config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 Please refer to the inline provider documentation.
 """,
@@ -640,7 +640,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.milvus",
             config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Milvus](https://milvus.io/) is an inline and remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly within a Milvus database.
@@ -846,7 +846,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.inline.vector_io.milvus",
             config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 Please refer to the remote provider documentation.
 """,
@@ -859,7 +859,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.elasticsearch",
             config_class="llama_stack.providers.remote.vector_io.elasticsearch.ElasticsearchVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Elasticsearch](https://www.elastic.co/) is a vector database provider for Llama Stack.
 It allows you to store and query vectors directly within an Elasticsearch database.
@@ -908,7 +908,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.oci",
             config_class="llama_stack.providers.remote.vector_io.oci.OCI26aiVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Oracle 26ai](https://docs.oracle.com/en/database/oracle/oracle-database/26/index.html)
 is a remote vector database provider for Llama Stack. It allows you to store and query vectors directly
@@ -957,7 +957,7 @@ def available_providers() -> list[ProviderSpec]:
             module="llama_stack.providers.remote.vector_io.infinispan",
             config_class="llama_stack.providers.remote.vector_io.infinispan.InfinispanVectorIOConfig",
             api_dependencies=[Api.inference],
-            optional_api_dependencies=[Api.files, Api.models],
+            optional_api_dependencies=[Api.files, Api.models, Api.file_processors],
             description="""
 [Infinispan](https://infinispan.org/) is a remote vector database provider for Llama Stack. It
 allows you to store and query vectors in a distributed Infinispan cluster via HTTP REST API.

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

@@ -12,6 +12,6 @@
 async def get_adapter_impl(config: ChromaVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .chroma import ChromaVectorIOAdapter
 
-    impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -22,6 +22,7 @@
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Inference,
     InsertChunksRequest,
@@ -247,8 +248,11 @@ def __init__(
         config: RemoteChromaVectorIOConfig | InlineChromaVectorIOConfig,
         inference_api: Inference,
         files_api: Files | None,
+        file_processor_api: FileProcessors | None = None,
     ) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         log.info(f"Initializing ChromaVectorIOAdapter with url: {config}")
         self.config = config
         self.client = None

src/llama_stack/providers/remote/vector_io/elasticsearch/__init__.py

@@ -12,6 +12,6 @@
 async def get_adapter_impl(config: ElasticsearchVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .elasticsearch import ElasticsearchVectorIOAdapter
 
-    impl = ElasticsearchVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = ElasticsearchVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -18,6 +18,7 @@
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Inference,
     InsertChunksRequest,
@@ -385,8 +386,11 @@ def __init__(
         config: ElasticsearchVectorIOConfig,
         inference_api: Inference,
         files_api: Files | None = None,
+        file_processor_api: FileProcessors | None = None,
     ) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         self.config = config
         self.client: AsyncElasticsearch = None
         self.cache = {}

src/llama_stack/providers/remote/vector_io/infinispan/__init__.py

@@ -12,6 +12,6 @@
 async def get_adapter_impl(config: InfinispanVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .infinispan import InfinispanVectorIOAdapter
 
-    impl = InfinispanVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))  # type: ignore[arg-type]
+    impl = InfinispanVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))  # type: ignore[arg-type]
     await impl.initialize()
     return impl

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

@@ -21,6 +21,7 @@
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Inference,
     InsertChunksRequest,
@@ -548,8 +549,11 @@ def __init__(
         config: InfinispanVectorIOConfig,
         inference_api: Inference,
         files_api: Files | None = None,
+        file_processor_api: FileProcessors | None = None,
     ) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         log.info(f"Initializing InfinispanVectorIOAdapter with config: {config}")
         self.config = config
         self.client: httpx.AsyncClient | None = None

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

@@ -13,6 +13,6 @@ async def get_adapter_impl(config: MilvusVectorIOConfig, deps: dict[Api, Provide
     from .milvus import MilvusVectorIOAdapter
 
     assert isinstance(config, MilvusVectorIOConfig), f"Unexpected config type: {type(config)}"
-    impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
+    impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files), deps.get(Api.file_processors))
     await impl.initialize()
     return impl

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

@@ -32,6 +32,7 @@
     CompoundFilter,
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Filter,
     Inference,
@@ -455,8 +456,11 @@ def __init__(
         config: RemoteMilvusVectorIOConfig | InlineMilvusVectorIOConfig,
         inference_api: Inference,
         files_api: Files | None,
+        file_processor_api: FileProcessors | None = None,
     ) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         self.config = config
         self.cache = {}
         self.client = None

src/llama_stack/providers/remote/vector_io/oci/__init__.py

@@ -12,11 +12,12 @@ async def get_adapter_impl(config: OCI26aiVectorIOConfig, deps: dict[Api, Provid
     from typing import cast
 
     from llama_stack.providers.remote.vector_io.oci.oci26ai import OCI26aiVectorIOAdapter
-    from llama_stack_api import Files, Inference
+    from llama_stack_api import FileProcessors, Files, Inference
 
     assert isinstance(config, OCI26aiVectorIOConfig), f"Unexpected config type: {type(config)}"
     inference_api = cast(Inference, deps[Api.inference])
     files_api = cast(Files | None, deps.get(Api.files))
-    impl = OCI26aiVectorIOAdapter(config, inference_api, files_api)
+    file_processor_api = cast(FileProcessors | None, deps.get(Api.file_processors))
+    impl = OCI26aiVectorIOAdapter(config, inference_api, files_api, file_processor_api)
     await impl.initialize()
     return impl

src/llama_stack/providers/remote/vector_io/oci/oci26ai.py

@@ -31,6 +31,7 @@
 from llama_stack_api import (
     DeleteChunksRequest,
     EmbeddedChunk,
+    FileProcessors,
     Files,
     Inference,
     InsertChunksRequest,
@@ -457,8 +458,11 @@ def __init__(
         config: OCI26aiVectorIOConfig,
         inference_api: Inference,
         files_api: Files | None,
+        file_processor_api: FileProcessors | None = None,
     ) -> None:
-        super().__init__(inference_api=inference_api, files_api=files_api, kvstore=None)
+        super().__init__(
+            inference_api=inference_api, files_api=files_api, kvstore=None, file_processor_api=file_processor_api
+        )
         self.config = config
         self.cache: dict[str, VectorStoreWithIndex] = {}
         self.pool = None