Search Results for "text database"

Paul Graham GPT is a specialized AI-powered search and chat app built on a corpus of essays from Paul Graham, giving users the ability to query and discuss his writings in a conversational way. The repo stores the full text of his essays (chunked), uses embeddings (e.g. via OpenAI embeddings) to allow semantic search over that corpus, and hosts a chat interface that combines retrieval results with LLM-based answering — enabling RAG (retrieval-augmented generation) over a fixed dataset. The app uses a Postgres database (with pgvector) hosted on Supabase for its embedding store, making the backend relatively simple and accessible, and the frontend is again built with Next.js/TypeScript for a modern responsive UI. ...

OpenSearchServer is a powerful, enterprise-class, search engine program. Using the web user interface, the crawlers (web, file, database, etc.) and the client libraries (REST/API , Ruby, Rails, Node.js, PHP, Perl) you will be able to integrate quickly and easily advanced full-text search capabilities in your application: Full-text with basic semantic, join queries, boolean queries, facet and filter, document (PDF, Office, etc.) indexation, web scrapping,etc. OpenSearchServer runs on Windows and Linux/Unix/BSD.

Infofuze is a Java library and server application that can be used to transform and combine data from various sources into a specific XML or other text output format that can be stored or indexed.

CLucene is a C++ port of Lucene: the high-performance, full-featured text search engine written in Java. CLucene is faster than lucene as it is written in C++.

A simple document management system (DMS). Documents and associated datas are stored in a single file. Keep all your documents in your pocket on your USB stick.

A Java implementation of a desktop search engine based on Apache Lucene. It indexes HTML-, XML-, OpenOffice- (Writer, Calc, Impress), MS Word-, and PDF- documents as well as plain text files. For other, arbitrary file types the file name can be indexed.

DuMP3 is a duplicate and similar file finder. It finds exact duplicate binaries by hash, similar text files by substring content, images (JPG, BMP, GIF, PNG, etc) by color and audio files (MP3, WAV, OGG, etc) by wave data. Future: fonts, video.

TiTLi: A Google-like, full-text search tool for relational databases. It is very fast and independent of vendor specific RDBMS's like mysql, oracle etc. It uses Apache Lucene for indexing and provides some advanced features like similarity search.