Dicklesworthstone / llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
☆2,609Updated last month
Alternatives and similar repositories for llm_aided_ocr:
Users that are interested in llm_aided_ocr are comparing it to the libraries listed below
- An open-source OCR API that leverages OpenAI's powerful language models with optimized performance techniques like parallel processing an…☆848Updated 6 months ago
- Detect and extract tables to markdown and csv☆737Updated 2 months ago
- Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.☆1,053Updated 3 months ago
- Improved file parsing for LLM’s☆2,909Updated 5 months ago
- Vision infrastructure to turn complex documents into RAG/LLM-ready data☆2,118Updated this week
- High-performance retrieval engine for unstructured data☆1,339Updated this week
- Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)☆582Updated last week
- DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception☆1,093Updated this week
- Lightweight, performant, deep table extraction☆449Updated 2 weeks ago
- This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.☆1,220Updated 2 weeks ago
- pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tid…☆2,508Updated 2 weeks ago
- Easily deployable 🚀 API to convert PDF to markdown quickly with high accuracy.☆834Updated 6 months ago
- RAG that intelligently adapts to your use case, data, and queries☆3,142Updated 2 weeks ago
- Extract structured text from pdfs quickly☆458Updated last month
- SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web☆1,213Updated this week
- NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other ent…☆2,642Updated this week
- OCR & Document Extraction using vision models☆10,962Updated this week
- ☆1,424Updated last month
- Empowering RAG with a memory-based data interface for all-purpose applications!☆1,734Updated last month
- mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding☆2,153Updated 3 months ago
- E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with ded…☆1,066Updated 7 months ago
- Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯☆832Updated last month
- A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The servic…☆465Updated 2 weeks ago
- 🔍 Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with 🧠 LLM.☆538Updated 2 months ago
- Document to Markdown OCR library with Llama 3.2 vision☆2,256Updated 2 months ago
- Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents…☆2,533Updated last week
- Open-source platform for extracting structured data from documents using AI.☆1,291Updated last month
- A simple, easy-to-hack GraphRAG implementation☆2,775Updated this week
- Things you can do with the token embeddings of an LLM☆1,435Updated 3 weeks ago
- Knowledge Agents and Management in the Cloud☆3,875Updated this week