phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 12:06:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Enable setting a default embedding model in the stack

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-10-14 00:22:49 -04:00
parent 007efa6eb5
commit 86c1e3b217
27 changed files with 435 additions and 403 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -11,6 +11,7 @@ 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
@ -75,6 +76,12 @@ 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)
@ -110,7 +117,7 @@ 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():
async def test_health_success(mock_models_api):
"""Test that the health check returns OK status when faiss is working correctly."""
# Create a fresh instance of FaissVectorIOAdapter for testing
config = MagicMock()
@ -119,7 +126,9 @@ async def test_health_success():
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, files_api=files_api)
adapter = FaissVectorIOAdapter(
config=config, inference_api=inference_api, models_api=mock_models_api, files_api=files_api
)
# Calling the health method directly
response = await adapter.health()
@ -133,7 +142,7 @@ async def test_health_success():
mock_index_flat.assert_called_once_with(128) # VECTOR_DIMENSION is 128
async def test_health_failure():
async def test_health_failure(mock_models_api):
"""Test that the health check returns ERROR status when faiss encounters an error."""
# Create a fresh instance of FaissVectorIOAdapter for testing
config = MagicMock()
@ -143,7 +152,9 @@ async def test_health_failure():
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, files_api=files_api)
adapter = FaissVectorIOAdapter(
config=config, inference_api=inference_api, models_api=mock_models_api, files_api=files_api
)
# Calling the health method directly
response = await adapter.health()