3 projects for "documents" with 2 filters applied:

  • Context for your AI agents Icon
    Context for your AI agents

    Crawl websites, sync to vector databases, and power RAG applications. Pre-built integrations for LLM pipelines and AI assistants.

    Build data pipelines that feed your AI models and agents without managing infrastructure. Crawl any website, transform content, and push directly to your preferred vector store. Use 10,000+ tools for RAG applications, AI assistants, and real-time knowledge bases. Monitor site changes, trigger workflows on new data, and keep your AIs fed with fresh, structured information. Cloud-native, API-first, and free to start until you need to scale.
    Try for free
  • Payments you can rely on to run smarter. Icon
    Payments you can rely on to run smarter.

    Never miss a sale. Square payment processing serves customers better with tools and integrations that make work more efficient.

    Accept payments at your counter or on the go. It’s easy to get started. Try the Square POS app on your phone or pick from a range of hardworking hardware.
    Learn More
  • 1
    libmwaw

    libmwaw

    Import library for legacy Mac documents

    libmwaw contains import filters for many old Macintosh text document formats (MacWrite, ClarisWorks, ... ) and for some graphic, spreadsheet and presentation formats. It can handle with varying level of success about forty different formats (see the Wiki section for more details). libmwaw is based on librevenge (see https://sourceforge.net/p/libwpd/wiki/librevenge/ ).
    Leader badge
    Downloads: 1,272 This Week
    Last Update:
    See Project
  • 2

    ftdetector

    File type detector library

    ...It uses hash tables to make the detection of a file type as fast as possible. The signature and mime types lists are stored at simple user-friendly files. This file type detector supports a lot of formats (image, archive, text, documents, audio, video, fonts and others). It also includes Microsoft OLE compound file types. The detector's algorythm has special features to detect text file types like (HTML, XML, JSON, etc.) and text file UNICODE charsets by using their BOMs (Byte order marks). Its small simple interface can be used at the most popular platforms.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 3
    reputron is a knowledge extraction engine platform that covers all aspect of text mining, relevance, indexing and querying on a corpus of text documents.
    Downloads: 0 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • Next