phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-07 10:50:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

Browse source 
# 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
Download patch file Download diff file Expand all files Collapse all files

19
tests/unit/providers/vector_io/test_faiss.py
View file

@ -11,7 +11,6 @@ import numpy as np
import pytest
from llama_stack.apis.files import Files
from llama_stack.apis.models import Models
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse
from llama_stack.providers.datatypes import HealthStatus
@ -76,12 +75,6 @@ def mock_files_api():
return mock_api
@pytest.fixture
def mock_models_api():
mock_api = MagicMock(spec=Models)
return mock_api
@pytest.fixture
def faiss_config():
config = MagicMock(spec=FaissVectorIOConfig)
@ -117,7 +110,7 @@ async def test_faiss_query_vector_returns_infinity_when_query_and_embedding_are_
assert response.chunks[1] == sample_chunks[1]
async def test_health_success(mock_models_api):
async def test_health_success():
"""Test that the health check returns OK status when faiss is working correctly."""
# Create a fresh instance of FaissVectorIOAdapter for testing
config = MagicMock()
@ -126,9 +119,7 @@ async def test_health_success(mock_models_api):
with patch("llama_stack.providers.inline.vector_io.faiss.faiss.faiss.IndexFlatL2") as mock_index_flat:
mock_index_flat.return_value = MagicMock()
adapter = FaissVectorIOAdapter(
config=config, inference_api=inference_api, models_api=mock_models_api, files_api=files_api
)
adapter = FaissVectorIOAdapter(config=config, inference_api=inference_api, files_api=files_api)
# Calling the health method directly
response = await adapter.health()
@ -142,7 +133,7 @@ async def test_health_success(mock_models_api):
mock_index_flat.assert_called_once_with(128) # VECTOR_DIMENSION is 128
async def test_health_failure(mock_models_api):
async def test_health_failure():
"""Test that the health check returns ERROR status when faiss encounters an error."""
# Create a fresh instance of FaissVectorIOAdapter for testing
config = MagicMock()
@ -152,9 +143,7 @@ async def test_health_failure(mock_models_api):
with patch("llama_stack.providers.inline.vector_io.faiss.faiss.faiss.IndexFlatL2") as mock_index_flat:
mock_index_flat.side_effect = Exception("Test error")
adapter = FaissVectorIOAdapter(
config=config, inference_api=inference_api, models_api=mock_models_api, files_api=files_api
)
adapter = FaissVectorIOAdapter(config=config, inference_api=inference_api, files_api=files_api)
# Calling the health method directly
response = await adapter.health()