Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jacoblee93/langchain-multimodal-hotdog-twilio
https://github.com/jacoblee93/langchain-multimodal-hotdog-twilio
Last synced: 9 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/jacoblee93/langchain-multimodal-hotdog-twilio
- Owner: jacoblee93
- License: mit
- Created: 2023-11-07T00:52:16.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2023-11-10T10:36:21.000Z (12 months ago)
- Last Synced: 2024-10-04T04:18:26.171Z (about 1 month ago)
- Language: TypeScript
- Size: 31.3 KB
- Stars: 8
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Multimodal GPT-4V Not Hotdog
OpenAI had a ton of awesome announcements at their most recent Developer Day, including multimodal support.
I immediately seized the opportunity to use billions of dollars of hard work and AI research to create the ultimate product:
a [Twilio](https://twilio.com) powered app that can detect whether an image contains a hotdog or not!It leverages GPT-4V, [LangChain.js](https://github.com/langchain-ai/langchainjs), and Twilio. The live deployment runs on a Cloudflare worker.
## Setup
First, you'll need a phone number with MMS capability from [Twilio](https://twilio.com).
You'll need to set your OpenAI key in `.dev.vars` and in your Cloudflare console:
```
OPENAI_API_KEY=
```Run `npm install`. You can run the `src/index.ts` file locally with `npx wrangler dev`, but it's easiest to test with a live Twilio number.
When you're ready, deploy with `npx wrangler deploy`. Take note of the URL and put it as the recipient webhook in Twilio.
And that's it! Text your phone number a picture, and it will respond with whether it's a hotdog or not.
## Thank you!
I hope this helps you eat healthier!
Thank you to [Craig](https://twitter.com/craigsdennis) and [Lizzie](https://twitter.com/lizziepika) for their help with this!
For more, follow me on X (formerly Twitter) [@Hacubu](https://x.com/hacubu/) and LangChain [@LangChainAI](https://x.com/LangChainAI/).