feat: Add synthetic-data-kit for file_search doc conversion

This adds a `builtin::document_conversion` tool for converting
documents when used with file_search that uses
meta-llama/synthetic-data-kit. I also have another local
implementation that uses Docling, but need to debug some segfault
issues I'm hitting locally with that so pushing this first as a
simpler reference implementation.

Long-term I think we'll want a remote implemention here as well - like
perhaps docling-serve or unstructured.io - but need to look more into
that.

This passes the existing
`tests/verifications/openai_api/test_responses.py` but doesn't yet add
any new tests for file types besides text and pdf.

Signed-off-by: Ben Browning <bbrownin@redhat.com>

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

@@ -16,6 +16,8 @@ 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, None))
+    impl = FaissVectorIOAdapter(
+        config, deps[Api.inference], deps.get(Api.files, None), deps.get(Api.tool_runtime, None)
+    )
     await impl.initialize()
     return impl

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

@@ -17,6 +17,7 @@ from numpy.typing import NDArray
 
 from llama_stack.apis.files import Files
 from llama_stack.apis.inference import Inference, InterleavedContent
+from llama_stack.apis.tools import ToolRuntime
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
@@ -149,10 +150,17 @@ class FaissIndex(EmbeddingIndex):
 
 
 class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
-    def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> None:
+    def __init__(
+        self,
+        config: FaissVectorIOConfig,
+        inference_api: Inference,
+        files_api: Files | None = None,
+        tool_runtime_api: ToolRuntime | None = None,
+    ) -> None:
         self.config = config
         self.inference_api = inference_api
         self.files_api = files_api
+        self.tool_runtime_api = tool_runtime_api
         self.cache: dict[str, VectorDBWithIndex] = {}
         self.kvstore: KVStore | None = None
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}

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

@@ -15,6 +15,8 @@ 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, None))
+    impl = SQLiteVecVectorIOAdapter(
+        config, deps[Api.inference], deps.get(Api.files, None), deps.get(Api.tool_runtime, None)
+    )
     await impl.initialize()
     return impl

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

@@ -17,6 +17,7 @@ from numpy.typing import NDArray
 
 from llama_stack.apis.files import Files
 from llama_stack.apis.inference import Inference
+from llama_stack.apis.tools import ToolRuntime
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
@@ -419,10 +420,13 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
     and creates a cache of VectorDBWithIndex instances (each wrapping a SQLiteVecIndex).
     """
 
-    def __init__(self, config, inference_api: Inference, files_api: Files | None) -> None:
+    def __init__(
+        self, config, inference_api: Inference, files_api: Files | None, tool_runtime_api: ToolRuntime | None
+    ) -> None:
         self.config = config
         self.inference_api = inference_api
         self.files_api = files_api
+        self.tool_runtime_api = tool_runtime_api
         self.cache: dict[str, VectorDBWithIndex] = {}
         self.openai_vector_stores: dict[str, dict[str, Any]] = {}