test_incremental_delete() — langchain Function Reference

Architecture documentation for the test_incremental_delete() function in test_indexing.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ test_incremental_delete() — langchain Function Reference

Dependency Diagram

graph TD
  06c70836_3e09_f7de_8a9e_11d7a57372ed["test_incremental_delete()"]
  a9fb4c74_0865_0941_ade3_563a79762cee["test_indexing.py"]
  06c70836_3e09_f7de_8a9e_11d7a57372ed -->|defined in| a9fb4c74_0865_0941_ade3_563a79762cee
  style 06c70836_3e09_f7de_8a9e_11d7a57372ed fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/indexing/test_indexing.py lines 1372–1482

def test_incremental_delete(
    record_manager: InMemoryRecordManager, vector_store: InMemoryVectorStore
) -> None:
    """Test indexing with incremental deletion strategy."""
    loader = ToyLoader(
        documents=[
            Document(
                page_content="This is a test document.",
                metadata={"source": "1"},
            ),
            Document(
                page_content="This is another document.",
                metadata={"source": "2"},
            ),
        ]
    )

    with patch.object(
        record_manager,
        "get_time",
        return_value=datetime(2021, 1, 1, tzinfo=timezone.utc).timestamp(),
    ):
        assert index(
            loader,
            record_manager,
            vector_store,
            cleanup="incremental",
            source_id_key="source",
            key_encoder="sha256",
        ) == {
            "num_added": 2,
            "num_deleted": 0,
            "num_skipped": 0,
            "num_updated": 0,
        }

    doc_texts = {
        # Ignoring type since doc should be in the store and not a None
        vector_store.get_by_ids([uid])[0].page_content
        for uid in vector_store.store
    }
    assert doc_texts == {"This is another document.", "This is a test document."}

    # Attempt to index again verify that nothing changes
    with patch.object(
        record_manager,
        "get_time",
        return_value=datetime(2021, 1, 2, tzinfo=timezone.utc).timestamp(),
    ):
        assert index(
            loader,
            record_manager,
            vector_store,
            cleanup="incremental",
            source_id_key="source",
            key_encoder="sha256",
        ) == {
            "num_added": 0,
            "num_deleted": 0,
            "num_skipped": 2,
            "num_updated": 0,
        }

    # Create 2 documents from the same source all with mutated content
    loader = ToyLoader(
        documents=[
            Document(
                page_content="mutated document 1",
                metadata={"source": "1"},
            ),
            Document(
                page_content="mutated document 2",
                metadata={"source": "1"},
            ),
            Document(
                page_content="This is another document.",  # <-- Same as original
                metadata={"source": "2"},
            ),
        ]
    )