feat: Add missing Vector Store Files API surface

This adds the ability to list, retrieve, update, and delete Vector
Store Files. It implements these new APIs for the faiss and sqlite-vec
providers, since those are the two that also have the rest of the
vector store files implementation.

There are a number of new integration tests added, which I ran for
each provider as outlined below.

faiss (from ollama distro):

```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack run llama_stack/templates/ollama/run.yaml

LLAMA_STACK_CONFIG=http://localhost:8321 \
pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \
  --embedding-model=all-MiniLM-L6-v2
```

sqlite-vec (from starter distro):

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

LLAMA_STACK_CONFIG=http://localhost:8321 \
pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \
  --embedding-model=all-MiniLM-L6-v2
```

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-06-18 09:14:22 -04:00
parent c20388c424
commit 459d50a365
11 changed files with 1248 additions and 20 deletions

View file

@ -21,7 +21,11 @@ from llama_stack.apis.vector_io import (
VectorStoreObject,
VectorStoreSearchResponsePage,
)
from llama_stack.apis.vector_io.vector_io import VectorStoreChunkingStrategy, VectorStoreFileObject
from llama_stack.apis.vector_io.vector_io import (
VectorStoreChunkingStrategy,
VectorStoreFileDeleteResponse,
VectorStoreFileObject,
)
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import HealthResponse, HealthStatus, RoutingTable
@ -279,6 +283,58 @@ class VectorIORouter(VectorIO):
chunking_strategy=chunking_strategy,
)
async def openai_list_files_in_vector_store(
self,
vector_store_id: str,
) -> list[VectorStoreFileObject]:
logger.debug(f"VectorIORouter.openai_list_files_in_vector_store: {vector_store_id}")
# Route based on vector store ID
provider = self.routing_table.get_provider_impl(vector_store_id)
return await provider.openai_list_files_in_vector_store(
vector_store_id=vector_store_id,
)
async def openai_retrieve_vector_store_file(
self,
vector_store_id: str,
file_id: str,
) -> VectorStoreFileObject:
logger.debug(f"VectorIORouter.openai_retrieve_vector_store_file: {vector_store_id}, {file_id}")
# Route based on vector store ID
provider = self.routing_table.get_provider_impl(vector_store_id)
return await provider.openai_retrieve_vector_store_file(
vector_store_id=vector_store_id,
file_id=file_id,
)
async def openai_update_vector_store_file(
self,
vector_store_id: str,
file_id: str,
attributes: dict[str, Any],
) -> VectorStoreFileObject:
logger.debug(f"VectorIORouter.openai_update_vector_store_file: {vector_store_id}, {file_id}")
# Route based on vector store ID
provider = self.routing_table.get_provider_impl(vector_store_id)
return await provider.openai_update_vector_store_file(
vector_store_id=vector_store_id,
file_id=file_id,
attributes=attributes,
)
async def openai_delete_vector_store_file(
self,
vector_store_id: str,
file_id: str,
) -> VectorStoreFileDeleteResponse:
logger.debug(f"VectorIORouter.openai_delete_vector_store_file: {vector_store_id}, {file_id}")
# Route based on vector store ID
provider = self.routing_table.get_provider_impl(vector_store_id)
return await provider.openai_delete_vector_store_file(
vector_store_id=vector_store_id,
file_id=file_id,
)
async def health(self) -> dict[str, HealthResponse]:
health_statuses = {}
timeout = 1 # increasing the timeout to 1 second for health checks