1. X
  2. Zylon
Log inSign up
Zylon
100 posts
Image
user avatar
Zylon
@ZylonPrivateGPT
The On-Premise AI Infrastructure for Regulated Industries keeping your data secure and cost fixed with unlimited tokens. Builders of PrivateGPT (57k GitHub ⭐)
zylon.ai
Joined October 2023
11
Following
1,365
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsΒ·PrivacyΒ·CookiesΒ·AccessibilityΒ·Ads InfoΒ·Β© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Oct 20, 2023
    PrivateGPT is a production-ready service offering Contextual Generative AI primitives like document ingestion and contextual completions through a new API that extends OpenAI’s standard. Talk to your documents privately using the default UI and RAG pipeline or integrate your own.
    16K016K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 29, 2023
    In case you missed today's @llama_index webinar "Building Production RAG with Local Models (featuring PrivateGPT)", here you can find the slides we presented with a complete overview of the project so far πŸ‘€ drive.google.com/file/d/1RxBjoE… Thanks to @jerryjliu0 for hosting the team πŸ™
    3.2K03.2K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Dec 10, 2023
    πŸš€ Exciting Project Update: v.0.2.0 is out!πŸš€ Contributors have been working hard transforming PrivateGPT for a faster, more secure, and customizable experience! 🌐 Dive into the details below πŸ‘‡
    Image
    4.6K04.6K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 25, 2023
    @llama_index has been a reference project for us since day 1, so we are proud to be speaking about PrivateGPT, RAG design, privacy in GenAI products and much more in their next webinar 😊 πŸ“Ί Join us and @jerryjliu0 on Wednesday at 9am PT lu.ma/i3ikz0ql
    user avatar
    LlamaIndex πŸ¦™
    @llama_index
    Nov 25, 2023
    Want to learn how to build a production-ready RAG stack using purely local models? We’re excited to be hosting a special webinar with @ivanmartit and @thanos_malkav on @PrivateGPT_AI - the leading project for privacy-aware RAG. it’s powered by @llama_index, and you can also
    Image
    6.2K06.2K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Feb 13, 2024
    πŸš€Β Big News! PrivateGPT expands its horizons with the introduction of Zylon, the AI collaborator for every workplace. Zylon emerges from stealth with a $3.2M Pre-Seed led by @Felicis to revolutionize GenAI usability and privacy. Join the beta at zylon.ai
    Image
    7.2K07.2K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 11, 2023
    Less than a month after releasing our new revamped version, PrivateGPT is back to being the Top Trending repository on @github πŸ₯‡ while passing the 40K stars ⭐️ THANKS everyone for your support!!! β™₯️ Stick around, great things are coming to this project and its community πŸš€
    PrivateGPT top trending repository on GitHub
    1.9K01.9K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Jan 5, 2024
    Really interesting way of bringing the power of ColBERT (github.com/stanford-futur…) to use advance retrieval techniques based on fine-grained contextual late interaction πŸ‘€ Should we create a new RAG implementation in PrivateGPT following this approach❓
    user avatar
    Ben ClaviΓ©
    Mixedbread
    @bclavie
    Jan 4, 2024
    The RAG wave is here to stay, but in practice, it's hard to retrieve the right docs w/ embdings, & better IR models are hard to use! Let's fix that: Introducing πŸͺ€RAGatouille, a lib to train&use SotA retrieval model, ColBERT, in just a few lines of code! github.com/bclavie/RAGato…
    Image
    2.5K02.5K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 20, 2023
    Happy to announce that @qdrant_engine has become the default #VectorDatabase for us πŸš€ As a result, we incorporate high-performance vector similarity search into #private AI applications πŸ’ͺ Cheers to a fantastic collaboration! πŸ‘ πŸ‘€ Integrations docs: qdrant.tech/documentation/…
    5.6K05.6K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 9, 2023
    πŸ“Ί @MatthewBerman just published a new great video describing all the new features we have recently launched youtu.be/XFiof0V3nhA?fe… πŸ™Thanks again for supporting us since day 1 and helping sharing the project with the community 🎁 Stay until the end for a little surprise!
    Image
    PrivateGPT 2.0 - FULLY LOCAL Chat With Docs (PDF, TXT, HTML, PPTX, DOCX, and more)
    From youtube.com
    1.3K01.3K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Nov 13, 2023
    πŸ“ƒ Sources in Completions API: Get info (text + metadata) about the Chunks used during inference by the contextual Completions APIs by adding: {"include_sources": true } to the request Body. Sources are enabled by default in the UI. πŸ‘©β€πŸ’» Docs: docs.privategpt.dev/#tag/Contextua…
    Image
    2.1K02.1K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Oct 25, 2023
    🧠PrivateGPT's Ingest API returns the *doc_id* and the extracted *doc_metadata* - btw, it works great with @llama_index's Metadata Extractors! Here are a few cool use cases that illustrate why this is incredibly useful for developers: 🧡
    Image
    1.2K01.2K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Jan 16, 2024
    Here is a great hands-on article by @CognitiveTech_ who uses @PrivateGPT_AI to compare the impact of - πŸ€– Models - πŸ”‘ Prompt styles - 🦾 System prompts - ✍️ User prompts on private, AI-powered book summarization Article: hackernoon.com/privategpt-for… Project: github.com/cognitivetech/…
    hackernoon.com
    PrivateGPT for Book Summarization: Testing and Ranking Configuration Variables | HackerNoon
    Summarizing books with local llm. My methods for testing and optimizing the use of PrivateGPT for book summaries.
    1.5K01.5K
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Oct 20, 2023
    Replying to @ZylonPrivateGPT
    πŸ’¬ And for those just wanting to talk to their documents in a plug-and-play way, we have made things easier with the new PrivateGPT UI! Now you can upload documents, select the interaction mode with your LLM (query, chat or chunks) and talk to it through a prompt.
    Image
    8590859
  • user avatar
    Zylon
    @ZylonPrivateGPT
    Jan 19, 2024
    πŸ—“οΈ 3 months ago we launched the brand new version of PGPT along with its Discord server and we are already 2.3K members collaborating on a daily basis in it: discord.gg/bK6mRVpErU Big thanks to this amazing community: you are the real fuel of this project πŸ₯°πŸš€
    8580858
Advertisement
Advertisement