Search Results for "semantic documents"

paperless-gpt is an AI-powered extension for document management systems that enhances the capabilities of paperless-ngx by integrating large language models and vision-based OCR to automate document processing and organization. It is designed to transform scanned or uploaded documents into structured, searchable, and intelligently categorized data without requiring manual tagging or sorting. The system uses OCR combined with LLM reasoning to extract text, classify documents, and generate metadata such as tags, titles, and categories automatically. It supports advanced workflows where documents can be analyzed contextually, enabling features like semantic search, summarization, and automated classification pipelines. ...

WeKnora is an open source framework developed for deep document understanding and semantic information retrieval using large language models. It focuses on analyzing complex and heterogeneous documents by combining multiple processing stages such as multimodal document parsing, vector indexing, and intelligent retrieval. It follows the Retrieval-Augmented Generation (RAG) paradigm, where relevant document segments are retrieved and used by language models to generate accurate, context-aware responses. ...

PandaWiki is an open source knowledge base system designed to help users build intelligent documentation platforms powered by large language models. It combines traditional wiki functionality with modern AI capabilities, allowing teams and individuals to create and manage product documentation, technical manuals, FAQs, and blog-style knowledge resources. PandaWiki provides tools for managing knowledge bases through an administrative interface while also generating public-facing wiki sites...

DefraDB is a Peer-to-Peer Edge Database. It's the core data storage system for the Source Network Ecosystem, built with IPFS/IPLD, LibP2P, CRDTs, and Semantic web3 properties. DefraDB is a user-centric database that prioritizes data ownership, personal privacy, and information security. Its data model, powered by the convergence of MerkleCRDTs and the content-addressability of IPLD, enables a multi-write-master architecture. It features DQL, a query language compatible with GraphQL but...