phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 10:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement embedding generation in supported inference providers (#589)

Browse source 
This PR adds the ability to generate embeddings in all supported
inference providers.

```
pytest -v -s llama_stack/providers/tests/inference/test_embeddings.py -k "bedrock" --inference-model="amazon.titan-embed-text-v2:0"  --env EMBEDDING_DIMENSION=1024

 pytest -v -s -k "vllm"  --inferrence-model="intfloat/e5-mistral-7b-instruct"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=4096  --env VLLM_URL="http://localhost:9798/v1"

pytest -v -s --inference-model="nomic-ai/nomic-embed-text-v1.5"  llama_stack/providers/tests/inference/test_embeddings.py  -k "fireworks"  --env FIREWORKS_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=128

pytest -v -s --inference-model="togethercomputer/m2-bert-80M-2k-retrieval"  llama_stack/providers/tests/inference/test_embeddings.py  -k "together"  --env TOGETHER_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=768

pytest -v -s -k "ollama"  --inference-model="all-minilm:v8"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384

 torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="sentence-transformers/all-MiniLM-L6-v2"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384

```
This commit is contained in:
Dinesh Yeduguru 2024-12-12 11:17:39 -08:00
parent 6a23f24ee0
commit d362d2d740
32 changed files with 597 additions and 143 deletions
Download patch file Download diff file Expand all files Collapse all files

80
llama_stack/providers/tests/memory/conftest.py
View file

@ -6,9 +6,65 @@
import pytest
from ..conftest import get_provider_fixture_overrides
from ..inference.fixtures import INFERENCE_FIXTURES
from .fixtures import MEMORY_FIXTURES
DEFAULT_PROVIDER_COMBINATIONS = [
pytest.param(
{
"inference": "meta_reference",
"memory": "faiss",
},
id="meta_reference",
marks=pytest.mark.meta_reference,
),
pytest.param(
{
"inference": "ollama",
"memory": "pgvector",
},
id="ollama",
marks=pytest.mark.ollama,
),
pytest.param(
{
"inference": "together",
"memory": "chroma",
},
id="chroma",
marks=pytest.mark.chroma,
),
pytest.param(
{
"inference": "bedrock",
"memory": "qdrant",
},
id="qdrant",
marks=pytest.mark.qdrant,
),
pytest.param(
{
"inference": "fireworks",
"memory": "weaviate",
},
id="weaviate",
marks=pytest.mark.weaviate,
),
]
def pytest_addoption(parser):
parser.addoption(
"--embedding-model",
action="store",
default=None,
help="Specify the embedding model to use for testing",
)
def pytest_configure(config):
for fixture_name in MEMORY_FIXTURES:
config.addinivalue_line(
@ -18,12 +74,22 @@ def pytest_configure(config):
def pytest_generate_tests(metafunc):
if "embedding_model" in metafunc.fixturenames:
model = metafunc.config.getoption("--embedding-model")
if not model:
raise ValueError(
"No embedding model specified. Please provide a valid embedding model."
)
params = [pytest.param(model, id="")]
metafunc.parametrize("embedding_model", params, indirect=True)
if "memory_stack" in metafunc.fixturenames:
metafunc.parametrize(
"memory_stack",
[
pytest.param(fixture_name, marks=getattr(pytest.mark, fixture_name))
for fixture_name in MEMORY_FIXTURES
],
indirect=True,
available_fixtures = {
"inference": INFERENCE_FIXTURES,
"memory": MEMORY_FIXTURES,
}
combinations = (
get_provider_fixture_overrides(metafunc.config, available_fixtures)
or DEFAULT_PROVIDER_COMBINATIONS
)
metafunc.parametrize("memory_stack", combinations, indirect=True)