.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/Basic-RAG/BasicRAG_ingest.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_Basic-RAG_BasicRAG_ingest.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_Basic-RAG_BasicRAG_ingest.py:

Document Ingestion
=======================
This cookbook demonstrates how to ingest pdf documents into a vector database.

.. GENERATED FROM PYTHON SOURCE LINES 5-30

.. code-block:: Python


    import asyncio
    from pathlib import Path

    from grag.components.multivec_retriever import Retriever
    from grag.components.vectordb.deeplake_client import DeepLakeClient

    client = DeepLakeClient(collection_name="grag")

    ## Alternatively to use Chroma
    # from grag.components.vectordb.chroma_client import ChromaClient
    # client = ChromaClient(collection_name="grag")

    ASYNC = True

    retriever = Retriever(vectordb=client)

    dir_path = (
        Path(__file__).parents[2] / "data/pdf"
    )  # path to the folder containing the pdfs

    if ASYNC:
        asyncio.run(retriever.aingest(dir_path))
    else:
        retriever.ingest(dir_path)


.. _sphx_glr_download_auto_examples_Basic-RAG_BasicRAG_ingest.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: BasicRAG_ingest.ipynb <BasicRAG_ingest.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: BasicRAG_ingest.py <BasicRAG_ingest.py>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_