https://github.com/labib2003/chat-with-pdf

AI chatbot powered by Google Generative AI API where you can upload a PDF file as the bots context and chat with it to extract information the file.
https://github.com/labib2003/chat-with-pdf

ai chatbot deno gemeni googlegenerativeai hono htmx rtc websocket

Last synced: 2 months ago
JSON representation

AI chatbot powered by Google Generative AI API where you can upload a PDF file as the bots context and chat with it to extract information the file.

• Host: GitHub
• URL: https://github.com/labib2003/chat-with-pdf
• Owner: Labib2003
• Created: 2024-11-21T07:39:52.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-21T08:01:14.000Z (over 1 year ago)
• Last Synced: 2025-01-22T05:28:41.780Z (over 1 year ago)
• Topics: ai, chatbot, deno, gemeni, googlegenerativeai, hono, htmx, rtc, websocket
• Language: TypeScript
• Homepage: https://chat-with-pdf-labib2003.deno.dev/
• Size: 5.86 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Chat with pdf

A Frankenstein project to try out a bunch of interesting technologies at once.

This is a AI chatbot powered by [Google Generative AI](https://ai.google.dev/) API where you can upload a PDF file as the bots context and chat with it to extract information the file.

## Key technologies used

- **Deno:** Backend runtime for secure and modern JavaScript/TypeScript development.

- **Hono:** Lightweight web framework for creating HTTP and WebSocket endpoints.

- **HTMX:** For building an interactive frontend with minimal JavaScript.

- **Tailwind CSS:** For styling the user interface efficiently.

## Limitations

Due to deno deploy not allowing disk access to store the uploaded files, the context is stored in memory. Thats why I had to limit the application to only accepting files up to 50kb and only 5 concurrent chat sessions to avoid crashes.

## Deployment

The application is deployed at Deno deploy.

[Live Demo](https://chat-with-pdf-labib2003.deno.dev/)