Published on November 28, 2024, the notebook presents a recipe for retrieval-augmented generation over PDF files using Docling and Weaviate. Docling is described as an open-source Python package that converts documents to Markdown or JSON.
Published on November 28, 2024, the notebook demonstrates a retrieval-augmented generation (RAG) workflow over PDFs using Docling and Weaviate. The description calls Docling an open-source Python package that converts documents, including PDFs, to Markdown or JSON.
The publication presents the material as a practical starting point for building this kind of pipeline; it does not report evaluation or performance results. Consult the original notebook in the public source archive and check its steps, dependencies, and any updates before reproducing the example.