Spine – Create and Share ChatGPT-like Interfaces on multi-modal data
Hey HN Community! We're excited to introduce Spine, a tool we've been developing for the past month that aims to streamline the process of building and sharing AI-driven natural language interfaces like ChatGPT for various data formats. With Spine, you can: * Upload numerous data types such as websites, PDFs, docs, PowerPoints, CSVs, audio files, YouTube videos, and more * Navigate lots of data and get in-depth referenced results with our hybrid search * Built-in Feedback: Craft accurate, personalized & adaptive experiences -- we will update the search models and eventually your LLM with the…
What it does
In the maker’s words, at launch
Hey HN Community! We're excited to introduce Spine, a tool we've been developing for the past month that aims to streamline the process of building and sharing AI-driven natural language interfaces like ChatGPT for various data formats. With Spine, you can: * Upload numerous data types such as websites, PDFs, docs, PowerPoints, CSVs, audio files, YouTube videos, and more * Navigate lots of data and get in-depth referenced results with our hybrid search * Built-in Feedback: Craft accurate, personalized & adaptive experiences -- we will update the search models and eventually your LLM with the feedback * Easy sharing: Seamlessly share your Spines so anyone can interact with your data (currently, you can share them on our website) Spine is currently powered by a few open-source libraries (HF, llama-index, etc.) along with OpenAI. We have designed Spine so that it should be simple to make it LLM-agnostic; we should be able to swap out GPT-3 (the default behaviour right now) for Cohere or an open-source LLM like FLAN or Bloom. We also want to make it trivial to embed Spine in any form -- and are currently working on making an API available so users can embed us on their website or slack. We also have a few known issues we are navigating through: https://sharing.clickup.com/9003104561/l/h/6-900301350489-1/.... A bit about us: we're Akshay and Ashwin, two passionate tech folks with backgrounds in AI, ML, and startups. Akshay is an AI lead at Georgian, where he helps growth-stage companies build ML products and has previously worked at two YC companies. Ashwin is a senior engineer at Instacart with previous experience at Alexa & Aurora (AWS) and NVIDIA. We studied ML together at the University of Waterloo and Nanyang Technological University on an exchange program some years ago. We created Spine in response to the growing demand for incorporating LLM-based chat interfaces into products and services in our companies. Our goal is to make this process as easy and accessible as possible. We're still in beta and eager to listen and gather your feedback. To facilitate this, we've prepared three demos that can be accessed without signing up (search through guides for hiring or getting hired remotely, some material from the All-in crew, and a demo on education highlighting some multi-modality). We also have a couple of loom videos if you want to see Spine in Action on the landing page! If you sign up (fingers crossed, everything runs smoothly), you can upload, create, and share as many Spines as you'd like for free! Please share any feedback or suggestions you may have. We're all ears!
Does the same job
all alternatives →
- AVA visual, knowledge map based interface for deep research/deep dives2025 · proread.ai · ▲8
I found myself jumping between ChatGPT, tabs, and docs, but never building real understanding. This is my attempt at fixing that — for researchers, curious readers, and lifelong learners. Would love your thoughts on the interface, and whether this would be useful in your own work or otherwise.
- CAChitchat, an easy-to-use, cross-platform, chat-based LLM interface2023 · clarkmccauley.com · ▲5
Just finished the first draft of my weekend project. Sadly my industry is far away from all the exciting machine learning developments happening right now, so I wrote this project as my first exploration into the world of LLMs. It's not perfect, but I'm excited to see where the project goes from here! https://github.com/clarkmcc/chitchat My main motivations were: - Easy-of-use: Many models are supported out-of-the-box so users don't have to figure out how to download, where to save, etc. - Intuitive: A clean interface - Cross platform: The project is written in Rust and…
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 · 27d ago · cactuscompute.com
Launched alongside, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
