sebarocks/chatsbt
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
Full-stack chat application that allows users to interact with multiple AI models through a web interface
13 commits 1 branch 0 tags 168 KiB
Find a file
Sebarocks c4eebafff6 more docker fixes
2025-07-31 22:50:03 -04:00
frontend more docker fixes 2025-07-31 22:50:03 -04:00
.gitignore Initial 2025-07-11 20:26:32 -04:00
app.py fixes icon and get parameter logic 2025-07-31 18:30:25 -04:00
chatgraph.py more docker fixes 2025-07-31 22:50:03 -04:00
controllers.py Multi model from api 2025-07-31 15:59:19 -04:00
Dockerfile more docker fixes 2025-07-31 22:50:03 -04:00
pyproject.toml Chat History and multi model 2025-07-29 23:42:15 -04:00
README.md added main readme 2025-07-30 00:10:33 -04:00
uv.lock Chat History and multi model 2025-07-29 23:42:15 -04:00

README.md

ChatSBT - Multi-Model Chat Application

A modern chat application supporting multiple AI models through OpenRouter API.

Features

  • Chat with multiple AI models (Qwen, Deepseek, Kimi)
  • Real-time streaming responses
  • Conversation history
  • Simple REST API backend
  • Modern Svelte frontend

Tech Stack

Frontend

  • Svelte
  • DaisyUI (Tailwind component library)
  • Vite

Backend

  • Starlette (async Python web framework)
  • LangChain (LLM orchestration)
  • LangGraph (for potential future agent workflows)
  • OpenRouter API (multi-model provider)

API Endpoints

Method Path Description
POST /chats Create new chat session
GET /chats/{chat_id} Get chat history
POST /chats/{chat_id}/messages Post new message
GET /chats/{chat_id}/stream Stream response from AI

Prerequisites

  • Python 3.11+
  • Deno
  • UV (Python package manager)
  • OpenRouter API key (set in .env file)

Installation

  1. Clone the repository
  2. Set up environment variables:
echo "OPENROUTER_API_KEY=your_key_here" > .env
echo "OPENROUTER_BASE_URL=https://openrouter.ai/api/v1" >> .env
  1. Install frontend dependencies:
cd chatsbt
deno install

Running

  1. Start backend server:
uv run app.py
  1. Start the frontend (another terminal):
cd chatsbt
deno run dev

The application will be available at http://localhost:5173

Configuration

Available models:

  • qwen/qwen3-235b-a22b-2507
  • deepseek/deepseek-r1-0528
  • moonshotai/kimi-k2