h2oGPTe Async API
=================
The `h2ogpte <https://pypi.org/project/h2ogpte/>`__ Python package also contains asynchronous version of API.
It offers the same capabilities as the synchronous version.

.. code-block:: python

    from pathlib import Path
    from h2ogpte import H2OGPTEAsync

    client = H2OGPTEAsync(
        address="https://h2ogpte.genai.h2o.ai",
        api_key=API_KEY,
    )

    # Create Collection
    collection_id = await client.create_collection(
        name="My first h2oGPTe collection",
        description="PDF -> text -> summary",
    )

    file_path = Path("...path to document(s)...")
    with open(file_path.resolve(), "rb") as f:
        upload_id = await client.upload(file_path.name, f)

    # Converting the input into chunked text and embeddings...
    await client.ingest_uploads(collection_id, [upload_id])

    # Chat with LLM
    chat_session_id = await client.create_chat_session(collection_id)
    async with client.connect(chat_session_id) as session:
        # Simple Question for Document Collection
        answer = await session.query(
            "What was net revenue?",
        )
        print(answer.content)