Developed an intelligent AI chatbot utilizing the DeepSeek LLM, designed for efficient interaction with large documents such as textbooks and study materials. Integrated Docling for parsing and processing large files, and implemented a Retrieval-Augmented Generation (RAG) pipeline using FAISS and Sentence Transformers to optimize context retrieval
Web app for PDF document ingestion with interactive preview, content editing, and vector database storage. Used for testing the similarity search
The MCP tool can then be used inside VS Code / MCP-enabled clients to search local internal documentation using natural language. Uses persistent embedding using minilm-l6-v2, supports multi format embedding and semantic retrieval .
A privacy-focused tool to extract structured content (tables, text) from PDFs into editable Word & CSV formats. Features offline translation and runs locally. Powered by Docling & Flask.
PDF-to-Markdown queue UI for Docling Serve
Add a description, image, and links to the docling topic page so that developers can more easily learn about it.
To associate your repository with the docling topic, visit your repo's landing page and select "manage topics."