CallGPT, 1 HTML file ChatGPT API client
I made a ChatGPT client that is contained in 1 HTML file. Would love to know what you guys think. The idea is to have something very simple to use that people can just download and use. If they want, tweak as per their liking. (You will need an OpenAI API to use it). - It doesn't call or use any 3rd party services (except jQuery and Bootstrap loaded from a CDN). Use your own API key, call the OpenAI API directly in its normal functioning ( there is a chatbot feature to pull top HN headlines which calls the HN API ). - Its just an HTML file, so you can run it from anywhere. Repo:…
What it does
In the maker’s words, at launch
I made a ChatGPT client that is contained in 1 HTML file. Would love to know what you guys think. The idea is to have something very simple to use that people can just download and use. If they want, tweak as per their liking. (You will need an OpenAI API to use it). - It doesn't call or use any 3rd party services (except jQuery and Bootstrap loaded from a CDN). Use your own API key, call the OpenAI API directly in its normal functioning ( there is a chatbot feature to pull top HN headlines which calls the HN API ). - Its just an HTML file, so you can run it from anywhere. Repo: https://github.com/dminGod/CallGPT Direct github pages demo: https://dmingod.github.io/CallGPT/chat_gpt.html - You can also use presets. For example, if I'm working on Golang -- I keep the Golang option selected. Now when I send a message saying : "how do I write a for loop?" it gets sent as --> "I am working on Golang. I need your help with how do I write a for loop?" (its fairly easy to change the names of technologies)" - Almost all API settings can be changed from the frontend (temprature, number of messages to generate etc.) I've added a few simple bot features to it as well that users can use as templates to make their own features: - You can request in the chat: 'change the background color of this page to <any color>' and it will reply back invoking a function to change the page color. Surprisingly it even works with vauge color descriptions like 'change the background color to the color of emma watsons eyes' :D - 'fetch the top hn stories' - Will pull up the latest HackerNews stories and show them in a 'Media' tab with Limitations: - It doesn't have context of previous calls made to it (but its not very hard to add, probably will add a setting to send previous x messages with the current message). - CORS severly limits the API calls that can be made from a local HTML file, so hooking it up with external services isn't straight forward for now - (I'm thinking of adding an external Golang app that will work with this page so the page can send it messages and the binary will do the heavy lifting)
Does the same job
all alternatives →
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, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io