Embeddings unit tests.
Base class for standard tests.
Embeddings tests base class.
Base class for embeddings unit tests.
Test subclasses must implement the embeddings_class property to specify the
embeddings model to be tested. You can also override the
embedding_model_params property to specify initialization parameters.
from typing import Type
from langchain_tests.unit_tests import EmbeddingsUnitTests
from my_package.embeddings import MyEmbeddingsModel
class TestMyEmbeddingsModelUnit(EmbeddingsUnitTests):
@property
def embeddings_class(self) -> Type[MyEmbeddingsModel]:
# Return the embeddings model class to test here
return MyEmbeddingsModel
@property
def embedding_model_params(self) -> dict:
# Return initialization parameters for the model.
return {"model": "model-001"}
API references for individual test methods include troubleshooting tips.
Testing initialization from environment variables
Overriding the init_from_env_params property will enable additional tests
for initialization from environment variables. See below for details.
init_from_env_paramsThis property is used in unit tests to test initialization from environment variables. It should return a tuple of three dictionaries that specify the environment variables, additional initialization args, and expected instance attributes to check.
Defaults to empty dicts. If not overridden, the test is skipped.
@property
def init_from_env_params(self) -> Tuple[dict, dict, dict]:
return (
{
"MY_API_KEY": "api_key",
},
{
"model": "model-001",
},
{
"my_api_key": "api_key",
},
)