test_chroma_large_batch_update() — langchain Function Reference

Source Code

libs/partners/chroma/tests/integration_tests/test_vectorstores.py lines 646–672

def test_chroma_large_batch_update() -> None:
    client = chromadb.HttpClient()
    embedding_function = MyEmbeddingFunction(fak=Fak(size=255))
    col = client.get_or_create_collection(
        "my_collection",
        embedding_function=embedding_function,  # type: ignore[arg-type]
    )
    docs = ["This is a test document"] * (client.get_max_batch_size() + 100)
    ids = [str(uuid.uuid4()) for _ in range(len(docs))]
    db = Chroma.from_texts(
        client=client,
        collection_name=col.name,
        texts=docs,
        embedding=embedding_function.fak,
        ids=ids,
    )
    new_docs = [
        Document(
            page_content="This is a new test document",
            metadata={"doc_id": f"{i}"},
        )
        for i in range(len(docs) - 10)
    ]
    new_ids = list(ids[: len(new_docs)])
    db.update_documents(ids=new_ids, documents=new_docs)

    db.delete_collection()