chore: Updating how default embedding model is set in stack (#3818)

# What does this PR do?

Refactor setting default vector store provider and embedding model to
use an optional `vector_stores` config in the `StackRunConfig` and clean
up code to do so (had to add back in some pieces of VectorDB). Also
added remote Qdrant and Weaviate to starter distro (based on other PR
where inference providers were added for UX).

New config is simply (default for Starter distro):

```yaml
vector_stores:
  default_provider_id: faiss
  default_embedding_model:
    provider_id: sentence-transformers
    model_id: nomic-ai/nomic-embed-text-v1.5
```

## Test Plan
CI and Unit tests.

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Francisco Arceo 2025-10-20 17:22:45 -04:00 committed by GitHub
parent 2c43285e22
commit 48581bf651
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
48 changed files with 973 additions and 818 deletions

View file

@ -121,6 +121,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
models = "models"
shields = "shields"
vector_dbs = "vector_dbs" # only used for routing
datasets = "datasets"
scoring_functions = "scoring_functions"
benchmarks = "benchmarks"

View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Literal
from typing import Literal, Protocol, runtime_checkable
from pydantic import BaseModel
@ -59,3 +59,35 @@ class ListVectorDBsResponse(BaseModel):
"""
data: list[VectorDB]
@runtime_checkable
class VectorDBs(Protocol):
"""Internal protocol for vector_dbs routing - no public API endpoints."""
async def list_vector_dbs(self) -> ListVectorDBsResponse:
"""Internal method to list vector databases."""
...
async def get_vector_db(
self,
vector_db_id: str,
) -> VectorDB:
"""Internal method to get a vector database by ID."""
...
async def register_vector_db(
self,
vector_db_id: str,
embedding_model: str,
embedding_dimension: int | None = 384,
provider_id: str | None = None,
vector_db_name: str | None = None,
provider_vector_db_id: str | None = None,
) -> VectorDB:
"""Internal method to register a vector database."""
...
async def unregister_vector_db(self, vector_db_id: str) -> None:
"""Internal method to unregister a vector database."""
...