Dicklesworthstone / llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
☆1,999Updated 3 weeks ago
Related projects: ⓘ
- Improved file parsing for LLM’s☆2,361Updated this week
- Zero shot pdf OCR with gpt-4o-mini☆1,392Updated this week
- Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model☆2,489Updated this week
- Open Source framework for voice and multimodal conversational AI☆3,044Updated this week
- A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!☆2,884Updated last month
- Parse files for optimal RAG☆2,450Updated this week
- The Open Source Memory Layer For Autonomous Agents☆1,390Updated last week
- High-performance retrieval engine for unstructured data☆778Updated this week
- WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.☆1,509Updated last month
- A vector search SQLite extension that runs anywhere!☆3,777Updated this week
- Infinite Bookshelf: Generate entire books in seconds using Groq and Llama3☆1,050Updated last week
- OCR, layout analysis, reading order, line detection in 90+ languages☆9,849Updated this week
- Easy token price estimates for 400+ LLMs. TokenOps.☆1,403Updated last week
- The Elasticsearch for RAG. Build, scale, and deploy state of the art Retrieval-Augmented Generation applications☆3,257Updated this week
- Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks☆4,988Updated 3 weeks ago
- RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry☆3,155Updated this week
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆2,739Updated last week