test_index_simple_delete_full() — langchain Function Reference

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

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ test_index_simple_delete_full() — langchain Function Reference

Dependency Diagram

graph TD
  7ae20361_226f_43e4_9060_02833115713b["test_index_simple_delete_full()"]
  a9fb4c74_0865_0941_ade3_563a79762cee["test_indexing.py"]
  7ae20361_226f_43e4_9060_02833115713b -->|defined in| a9fb4c74_0865_0941_ade3_563a79762cee
  style 7ae20361_226f_43e4_9060_02833115713b fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/indexing/test_indexing.py lines 152–258

def test_index_simple_delete_full(
    record_manager: InMemoryRecordManager, vector_store: InMemoryVectorStore
) -> None:
    """Indexing some content to confirm it gets added only once."""
    loader = ToyLoader(
        documents=[
            Document(
                page_content="This is a test document.",
            ),
            Document(
                page_content="This is another document.",
            ),
        ]
    )

    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="full",
            key_encoder="sha256",
        ) == {
            "num_added": 2,
            "num_deleted": 0,
            "num_skipped": 0,
            "num_updated": 0,
        }

    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="full",
            key_encoder="sha256",
        ) == {
            "num_added": 0,
            "num_deleted": 0,
            "num_skipped": 2,
            "num_updated": 0,
        }

    loader = ToyLoader(
        documents=[
            Document(
                page_content="mutated document 1",
            ),
            Document(
                page_content="This is another document.",  # <-- Same as original
            ),
        ]
    )

    with patch.object(
        record_manager,
        "get_time",
        return_value=datetime(2021, 1, 2, tzinfo=timezone.utc).timestamp(),
    ):
        indexing_result = index(
            loader,
            record_manager,
            vector_store,
            cleanup="full",
            key_encoder="sha256",
        )

        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 == {"mutated document 1", "This is another document."}