feat: File search tool for Responses API (#2426)

# What does this PR do?

This is an initial working prototype of wiring up the `file_search`
builtin tool for the Responses API to our existing rag knowledge search
tool.

This is me seeing what I could pull together on top of the bits we
already have merged. This may not be the ideal way to implement this,
and things like how I shuffle the vector store ids from the original
response API tool request to the actual tool execution feel a bit hacky
(grep for `tool_kwargs["vector_db_ids"]` in `_execute_tool_call` to see
what I mean).

## Test Plan

I stubbed in some new tests to exercise this using text and pdf
documents.

Note that this is currently under tests/verification only because it
sometimes flakes with tool calling of the small Llama-3.2-3B model we
run in CI (and that I use as an example below). We'd want to make the
test a bit more robust in some way if we moved this over to
tests/integration and ran it in CI.

### OpenAI SaaS (to verify test correctness)

```
pytest -sv tests/verifications/openai_api/test_responses.py \
  -k 'file_search' \
  --base-url=https://api.openai.com/v1 \
  --model=gpt-4o
```

### Fireworks with faiss vector store

```
llama stack run llama_stack/templates/fireworks/run.yaml

pytest -sv tests/verifications/openai_api/test_responses.py \
  -k 'file_search' \
  --base-url=http://localhost:8321/v1/openai/v1 \
  --model=meta-llama/Llama-3.3-70B-Instruct
```

### Ollama with faiss vector store

This sometimes flakes on Ollama because the quantized small model
doesn't always choose to call the tool to answer the user's question.
But, it often works.

```
ollama run llama3.2:3b

INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack run ./llama_stack/templates/ollama/run.yaml \
  --image-type venv \
  --env OLLAMA_URL="http://0.0.0.0:11434"

pytest -sv tests/verifications/openai_api/test_responses.py \
  -k'file_search' \
  --base-url=http://localhost:8321/v1/openai/v1 \
  --model=meta-llama/Llama-3.2-3B-Instruct
```

### OpenAI provider with sqlite-vec vector store

```
llama stack run ./llama_stack/templates/starter/run.yaml --image-type venv

 pytest -sv tests/verifications/openai_api/test_responses.py \
  -k 'file_search' \
  --base-url=http://localhost:8321/v1/openai/v1 \
  --model=openai/gpt-4o-mini
```

### Ensure existing vector store integration tests still pass

```
ollama run llama3.2:3b

INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack run ./llama_stack/templates/ollama/run.yaml \
  --image-type venv \
  --env OLLAMA_URL="http://0.0.0.0:11434"

LLAMA_STACK_CONFIG=http://localhost:8321 \
pytest -sv tests/integration/vector_io \
  --text-model "meta-llama/Llama-3.2-3B-Instruct" \
  --embedding-model=all-MiniLM-L6-v2
```

---------

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

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])
+    impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
     await impl.initialize()
     return impl

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

@@ -15,6 +15,7 @@ import faiss
 import numpy as np
 from numpy.typing import NDArray
 
+from llama_stack.apis.files import Files
 from llama_stack.apis.inference import InterleavedContent
 from llama_stack.apis.inference.inference import Inference
 from llama_stack.apis.vector_dbs import VectorDB
@@ -132,9 +133,10 @@ class FaissIndex(EmbeddingIndex):
 
 
 class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
-    def __init__(self, config: FaissVectorIOConfig, inference_api: Inference) -> None:
+    def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> 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]] = {}

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])
+    impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
     await impl.initialize()
     return impl

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

@@ -17,6 +17,7 @@ import numpy as np
 import sqlite_vec
 from numpy.typing import NDArray
 
+from llama_stack.apis.files.files import Files
 from llama_stack.apis.inference.inference import Inference
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
@@ -301,9 +302,10 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
     and creates a cache of VectorDBWithIndex instances (each wrapping a SQLiteVecIndex).
     """
 
-    def __init__(self, config, inference_api: Inference) -> None:
+    def __init__(self, config, inference_api: Inference, files_api: Files | None) -> 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]] = {}