unstructured-io

Collection of PDF parsing libraries like AI based docling, claude, openai, gemini, meta's llama-vision, unstructured-io, and pdfminer, pymupdf, pdfplumber etc for efficient snapshot, text, table, and metadata extraction.

Extract data from images, pdf, invoices, receipts | Extract tables from pdf, images and convert to Excel/CSV | OCR complex pdfs, images.

This is a collection of various document parsers and hands-on to construct structured data for your RAG applications.

Multi-Modal RAG: An AI-powered pipeline for extracting, chunking, and summarizing content from PDF documents using advanced chunking strategies and generative models. Includes support for text, tables, and images, with vector search and retrieval via ChromaDB.

Atlas v0.2 - Your personal knowledgebase

Parallel preprocessing toolkit for an unstructured-mesh in CGNS format (parallel read + partition + geometry)

Atlas v0.1

A Python pipeline that converts PDF documents into searchable vector embeddings and persists them in a local ChromaDB collection. Built with unstructured, sentence-transformers, and managed with uv.

Run unstructured io locally without restriction to analyze text in files or images

A GUI to select and annotate PDF areas with the help of Unstructured API and ChatGPT.

This Advanced Multimodal RAG system enables secure, offline querying of complex PDF documents. It uses unstructured to ingest text, tables, and images, generates summaries via local LLMs (Ollama/Llama 3), and retrieves context using ChromaDB to answer user queries through a Gradio chat interface.

Developed an end-to-end Multimodal Retrieval-Augmented Generation (RAG) ingestion pipeline for processing complex PDF documents containing text, tables, and images. • Implemented high-resolution PDF parsing using Unstructured.io with OCR support for scanned documents, enabling extraction text, tables, and embedded images while preserving document

Technical Report Generation and Editing using GenAI

Benchmark open-source document parsers for RAG and LLM applications.

Streamlit based Chatbot for Tech and Non-Tech Customer Queries using CrewAI framework to showcase RAG based AgenticAI

Documentation assistant for developers who want to quickly understand and query large documentation sites. Built with a modern tech stack including Firecrawl for llm-ready web crawling, Unstructured for document processing, MongoDB Atlas for vector search, and OpenAI for embeddings and generation.

Analyze research documents using knowledge graphs and LLM-powered retrieval to extract intelligence for unmanned systems.