mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
32d1e50a6f
# What does this PR do? This is a follow on to #1022 . It includes the changes I needed to be able to test the Qdrant support as requested by @terrytangyuan . I uncovered a lot of bigger, more systemic issues with the vector DB testing and I will open a new issue for those. For now, I am just delivering the work I already did on that. ## Test Plan As discussed on #1022: ``` podman pull qdrant/qdrant mkdir qdrant-data podman run -p 6333:6333 -v $(pwd)/qdrant-data:/qdrant/storage qdrant/qdrant ``` ``` ollama pull all-minilm:l6-v2 curl http://localhost:11434/api/embeddings -d '{"model": "all-minilm", "prompt": "Hello world"}' ``` ``` EMBEDDING_DIMENSION=384 QDRANT_URL=http://localhost pytest llama_stack/providers/tests/vector_io/test_vector_io.py -m "qdrant" -v -s --tb=short --embedding-model all-minilm:latest --disable-warnings ``` These show 3 tests passing and 15 deselected which is presumably working as intended. --------- Signed-off-by: Bill Murdock <bmurdock@redhat.com>
108 lines
3 KiB
Python
108 lines
3 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
|
|
from ..conftest import (
|
|
get_provider_fixture_overrides,
|
|
get_provider_fixture_overrides_from_test_config,
|
|
get_test_config_for_api,
|
|
)
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from .fixtures import VECTOR_IO_FIXTURES
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"inference": "sentence_transformers",
|
|
"vector_io": "faiss",
|
|
},
|
|
id="sentence_transformers",
|
|
marks=pytest.mark.sentence_transformers,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"vector_io": "pgvector",
|
|
},
|
|
id="pgvector",
|
|
marks=pytest.mark.pgvector,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"vector_io": "faiss",
|
|
},
|
|
id="ollama",
|
|
marks=pytest.mark.ollama,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"vector_io": "sqlite_vec",
|
|
},
|
|
id="sqlite_vec",
|
|
marks=pytest.mark.ollama,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "sentence_transformers",
|
|
"vector_io": "chroma",
|
|
},
|
|
id="chroma",
|
|
marks=pytest.mark.chroma,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"vector_io": "qdrant",
|
|
},
|
|
id="qdrant",
|
|
marks=pytest.mark.qdrant,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "fireworks",
|
|
"vector_io": "weaviate",
|
|
},
|
|
id="weaviate",
|
|
marks=pytest.mark.weaviate,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for fixture_name in VECTOR_IO_FIXTURES:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{fixture_name}: marks tests as {fixture_name} specific",
|
|
)
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
test_config = get_test_config_for_api(metafunc.config, "vector_io")
|
|
if "embedding_model" in metafunc.fixturenames:
|
|
model = getattr(test_config, "embedding_model", None)
|
|
# Fall back to the default if not specified by the config file
|
|
model = model or metafunc.config.getoption("--embedding-model")
|
|
if model:
|
|
params = [pytest.param(model, id="")]
|
|
else:
|
|
params = [pytest.param("all-minilm:l6-v2", id="")]
|
|
|
|
metafunc.parametrize("embedding_model", params, indirect=True)
|
|
|
|
if "vector_io_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"inference": INFERENCE_FIXTURES,
|
|
"vector_io": VECTOR_IO_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides_from_test_config(metafunc.config, "vector_io", DEFAULT_PROVIDER_COMBINATIONS)
|
|
or get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("vector_io_stack", combinations, indirect=True)
|