A protocol for sharing knowledge via semantic lookup with use in LLMs
A great way to enhance chatbots is to allow them to look up information for context, typically using a vectordb. If you have writings you would like to share with others, you can offer a server that allows others to do semantic lookup, and that way anyone can have a chatbot which can pull from your writing. The goal of this project is to have a protocol that makes that easy. Strictly speaking, the protocol is for semantic retrieval and doesn't require using LLMs although LLMs are the motivating application. For far more details and how to get a demo up and running, see the readme.
In plain words
This project provides a protocol for semantic lookup that enables people to share their written content with chatbots and other applications. Users can run a server offering semantic retrieval from their writings, allowing others to build chatbots that access that knowledge base. While designed to enhance large language models with contextual information typically stored in vector databases, the protocol works for semantic retrieval generally. It aims to standardize how knowledge sharing works across different systems and applications.
written from the facts on this page · September 2026
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2024
the whole month →
- IM
Life & fun · 2024 · sitinshade.com
