InsightFlow
Hey everyone, sharing InsightFlow, a (long) weekend project I made using GPT4. I am bit anxious sharing it since I barely knew how to code in Python before but I was simply amazed on how much GPT was able to help me write something that actually works (I hope). My goal was to create a library that empowers people to ask questions from their data, regardless of its source. InsightFlow does just that, it has some modules that allow s parsing information existing in (for now) video (its audio part), html, and in general text and provides a chat interface on top. I would love to expand this to…
In plain words
InsightFlow is an open-source library that lets users ask questions about data from multiple sources including video audio, HTML, and text. It parses information from these formats and provides a chat interface for querying the data. Built with GPT-4, the tool is designed to be modular, allowing for expansion to image and video parsing. InsightFlow is intended for anyone wanting to interact conversationally with their data regardless of its source format.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey everyone, sharing InsightFlow, a (long) weekend project I made using GPT4. I am bit anxious sharing it since I barely knew how to code in Python before but I was simply amazed on how much GPT was able to help me write something that actually works (I hope). My goal was to create a library that empowers people to ask questions from their data, regardless of its source. InsightFlow does just that, it has some modules that allow s parsing information existing in (for now) video (its audio part), html, and in general text and provides a chat interface on top. I would love to expand this to image and eventually video parsing. I know there are some companies that aim for the same but I could not find an opensouce alternative for it. I tried making it modular so different modalities can be added later on.
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 · 16d 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, 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
