Skip to content

Implement LangChain standard integration tests for VectorStore #39

@webup

Description

@webup

Labels: testing, langchain-community, difficulty:medium
LOC: ~200

Description

Add standard integration tests from langchain-tests package.

References

Tasks

  • Create tests/integration_tests/test_vectorstore_standard.py
  • Implement VectorStoreIntegrationTests subclass
  • Configure feature flags (supports_mmr, supports_filter, etc.)
  • Run tests with OceanBase/SeekDB

Sample AI Prompts

Study https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/tests/integration_tests/test_vectorstores.py
and create standard integration tests for OceanbaseVectorStore by subclassing VectorStoreIntegrationTests.
Include a pytest fixture that creates an empty vector store connected to a test database.
Review OceanbaseVectorStore to determine which feature flags to enable (supports_mmr, supports_filter, etc.)
Read langchain_oceanbase/vectorstores.py and identify all capabilities that OceanbaseVectorStore supports.
Map these to the feature flag properties in VectorStoreIntegrationTests base class.
Run the integration tests against SeekDB and fix any failures:
docker-compose -f docker-compose.seekdb.yml up -d
pytest tests/integration_tests/test_vectorstore_standard.py -v

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions