CodePrompt – a UI for loading code repos into GPT prompts
Hi HN, I'm Chun Rapeepat. Last week I started playing with GPT-4 and tried different ways to use it to optimize my dev workflow. It was fun, and I was just blown away by what GPT-4 can do. The idea of CodePrompt first came to mind when I read "Show HN: GPT Repo Loader – load entire code repos into GPT prompts" [1]. It was precisely what I wanted to do! So I tried it. The GPT Repo Loader works pretty well on a small codebase; However, due to its limitations in loading all files and content into the prompt, I still ran into token context limit issues and needed to copy/edit the code…
What it does
In the maker’s words, at launch
Hi HN, I'm Chun Rapeepat. Last week I started playing with GPT-4 and tried different ways to use it to optimize my dev workflow. It was fun, and I was just blown away by what GPT-4 can do. The idea of CodePrompt first came to mind when I read "Show HN: GPT Repo Loader – load entire code repos into GPT prompts" [1]. It was precisely what I wanted to do! So I tried it. The GPT Repo Loader works pretty well on a small codebase; However, due to its limitations in loading all files and content into the prompt, I still ran into token context limit issues and needed to copy/edit the code myself. That's when I started working on CodePrompt. Instead of loading the entire repo, why not just load only relevant files or portions of code (or function headers?) that need for the requirement? How I designed the user journey of CodePrompt.xyz: 1. Choose a GPT model. 2. Select a repo that you want to work with. 3. Pick the relevant files that you want to include in the prompt. 4. Add specific instructions and remove irrelevant codes as needed. 5. Copy the prompt to your chosen GPT model to generate the desired output. Chat & Iterate. 6. If you want to do something else, just go to (3) again. This allows me to easily generate prompts to do something like - Implement features that evolve edits on multiple files - Create new components while reusing existing codebase - Generate code with the same style as other files, etc. I would love to hear all your feedback and ideas on how I can improve it. Or if you want to chat, feel free to ping me on my Twitter @chunrapeepat. P.S. The project is 100% open-source and free to use. Check it out: https://github.com/chunrapeepat/codeprompt [1] https://news.ycombinator.com/item?id=35191303
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 · 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, 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