Sankofa – Chat with the Browser History
Hey Hackernews, I'm Ofer, head of developer relations at Vectara. Some of us read a lot of articles on the web, like those on HN, and it seems useful to be able to search the contents of the text we read (using semantic search), or ask questions about it (ChatGPT style). Sankofa is a new browser extension that allows you to index web pages you visit and search / ask questions about that content. We built it using Vectara's retrieval-augmented-generation (RAG) platform and hope this is useful to folks. This is an initial release - we would love to hear any feedback and suggestions. BTW,…
What it does
In the maker’s words, at launch
Hey Hackernews, I'm Ofer, head of developer relations at Vectara. Some of us read a lot of articles on the web, like those on HN, and it seems useful to be able to search the contents of the text we read (using semantic search), or ask questions about it (ChatGPT style). Sankofa is a new browser extension that allows you to index web pages you visit and search / ask questions about that content. We built it using Vectara's retrieval-augmented-generation (RAG) platform and hope this is useful to folks. This is an initial release - we would love to hear any feedback and suggestions. BTW, Sankofa which means "to retrieve" in the Twi language of Ghana.
Does the same job
all alternatives →
- IBI built a Chrome extension to declutter ChatGPT2024 · pinfold.me · ▲9
Hey HN, Like many of you, I’ve been using ChatGPT to brainstorm, debug code, and even plan projects. But as the number of conversations grew, I found myself scrolling endlessly trying to find old chats. It was frustrating and unproductive. So, I built PinFold – a Chrome extension to help manage and organize ChatGPT conversations. With PinFold, you can: Pin important chats for quick access. Organize conversations into folders (e.g., personal vs. work-related). Declutter your ChatGPT history and boost productivity. It's privacy-focused: no data is sent to external servers – everything is…
- CHChatGPT History Explorer2023 · github.com · ▲7
Hey HN, As a heavy ChatGPT user, I often want to explore my chat history, look for things I've already asked, keep favorite chats, and much more. ChatGPT doesn't even offer search capability (except in mobile version). So I decided to build one myself. It runs locally, so no sensitive data leaks. You only need to export your ChatGPT conversations, and put it in the `data` folder. Optionally setup OpenAI API key and it will create embeddings for semantic search. *Important* - it's not a desktop app (at least, not yet) - it's a python code with a browser interface that I've only tested on…
- WAWe added ChatGPT to our documentation to make them fully portable2023 · xata.io · ▲7
TLDR: Check out our documentation search here: https://xata.io/docs/overview Hello HN. I'm a designer over at Xata. We build a serverless database platform on top of Postgres and Elastic-like search that provides goodies like a native TypeScript client for type support in your IDE. Long story short, we're trying to bundle all the normal stuff you need out of a database along with branching, so you don't have to glue everything together. Today we added a new /ask/ endpoint to our search product that bundles in ChatGPT support into any stored data. Why would you…
- BEBrowser extension to summarize HN comments – bring your own AI models2024 · github.com · ▲8
We’re George and Ann, and want to share a Hacker News specific browser extension that we have been working on. We all love the rich discussions in HN, but navigating long posts with multiple threads can sometimes be challenging. You get lost in the depth and breadth of the discussion. There are a few AI-based summarization tools, but they typically focus on summarizing the article rather than the comments, and thus miss the essence of threaded discussions. So, we built Hacker News Companion, a browser extension that makes it easy to navigate discussions and understand diverse viewpoints…
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
