test_add_documents_with_existing_ids() — langchain Function Reference

Source Code

libs/standard-tests/langchain_tests/integration_tests/vectorstores.py lines 440–484

    def test_add_documents_with_existing_ids(self, vectorstore: VectorStore) -> None:
        """Test that `add_documents` with existing IDs is idempotent.

        ??? note "Troubleshooting"

            If this test fails, check that `get_by_ids` is implemented and returns
            documents in the same order as the IDs passed in.

            This test also verifies that:

            1. IDs specified in the `Document.id` field are assigned when adding
                documents.
            2. If some documents include IDs and others don't string IDs are generated
                for the latter.

            !!! note
                `get_by_ids` was added to the `VectorStore` interface in
                `langchain-core` version 0.2.11. If difficult to implement, this
                test can be skipped by setting the `has_get_by_ids` property to
                `False`.

                ```python
                @property
                def has_get_by_ids(self) -> bool:
                    return False
                ```
        """
        if not self.has_sync:
            pytest.skip("Sync tests not supported.")

        if not self.has_get_by_ids:
            pytest.skip("get_by_ids not implemented.")

        documents = [
            Document(id="foo", page_content="foo", metadata={"id": 1}),
            Document(page_content="bar", metadata={"id": 2}),
        ]
        ids = vectorstore.add_documents(documents)
        assert "foo" in ids
        assert _sort_by_id(vectorstore.get_by_ids(ids)) == _sort_by_id(
            [
                Document(page_content="foo", metadata={"id": 1}, id="foo"),
                Document(page_content="bar", metadata={"id": 2}, id=ids[1]),
            ]
        )