Team Ai
Apppublic

SalimBinYousuf/optimized-deepseek-chatbot

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes
App README

AI Chatbot with DeepSeek Integration

This repository contains a powerful AI chatbot built with DeepSeek model integration, featuring advanced capabilities including instruction-following, multi-turn conversations, Markdown rendering, code understanding, and more.

Features

Core AI Features

  • —Instruction Following: The model follows prompts like ChatGPT
  • —Multi-turn Conversations: Keeps track of session history for context
  • —Markdown Support: Renders headings, lists, code blocks, and tables
  • —Urdu Nastaliq Rendering: Full support for Nastaliq-style Urdu text
  • —Math & Logic Reasoning: Solves equations and explains steps
  • —Code Understanding: Writes and explains code with syntax support
  • —Error Detection: Highlights and fixes errors in code and language
  • —Text Summarization: Condenses content into concise summaries
  • —Image Interpretation: Extracts text from images

Frontend UI Features

  • —Chat Interface: Real-time chat with typing effect and editable responses
  • —Code Editor: In-browser editor with syntax highlighting and a bash terminal
  • —File Manager: Upload, download, preview files (PDF, code, images)
  • —Dark/Light Mode: Toggle themes with Tailwind CSS
  • —Voice Interaction: Speech-to-text and text-to-speech capabilities

Technology Stack

Backend

  • —FastAPI: High-performance API framework
  • —WebSockets: Real-time communication
  • —PyJWT: Authentication and session management
  • —Hugging Face Integration: DeepSeek model access

Frontend

  • —Next.js: React framework for UI
  • —Tailwind CSS: Utility-first styling
  • —Monaco Editor: VS Code-like code editor
  • —React Markdown: Markdown rendering

Deployment

This application is deployed as a Hugging Face Space using Docker.

Getting Started

Prerequisites

  • —Python 3.10+
  • —Node.js 20+
  • —Hugging Face API key

Installation

  1. 1.Clone the repository
bash
git clone https://huggingface.co/spaces/[your-username]/deepseek-chatbot
cd deepseek-chatbot
  1. 1.Install backend dependencies
bash
cd backend
pip install -r requirements.txt
  1. 1.Install frontend dependencies
bash
cd frontend
npm install
  1. 1.Set up environment variables Create a .env file in the root directory with:
HUGGINGFACE_API_KEY=your_api_key_here
  1. 1.Run the application
bash
# Start the backend
uvicorn backend.main:app --reload

# In another terminal, start the frontend
cd frontend
npm run dev

License

MIT