or-chat

A sleek, modern chatbot powered by free LLMs from OpenRouter

Accessible AI conversations with cutting-edge language models

---

Features

• 💬 Real-time Streaming - Get responses as they're generated
• 🛡️ Secure API Key Management - Your credentials stay private
• 🚀 Powered by Z-AI GLM - Advanced Z-ai/glm-4.5-air:free model
• 📊 Conversation History - Persistent chat sessions
• 🎨 Modern UI - Built with Streamlit for a clean interface
• 🛠️ Production Ready - Secure, efficient, and reliable

Architecture

graph LR
    A[User Input] --> B[Streamlit Frontend]
    B --> C[API Key Validation]
    C --> D[OpenRouter API]
    D --> E[Z-ai/glm-4.5-air:free]
    E --> D
    D --> F[Response Streaming]
    F --> G[Streamlit Display]
    G --> H[Conversation History]
    H --> B

Loading

Quick Start

Prerequisites

• Python 3.8+
• OpenRouter API Key

Installation

1. Clone the repository

   git clone https://github.com/BLShaw/or-chat.git
   cd or-chat

2. Install dependencies

   pip install -r requirements.txt

3. Set up environment variables

   cp .env.example .env

   Edit .env and add your OpenRouter API key:

   OPENROUTER_API_KEY=your_actual_api_key_here
   

4. Launch the application

   streamlit run app.py

Your chatbot will be available at http://localhost:8501

User Workflow

sequenceDiagram
    participant U as User
    participant S as Streamlit UI
    participant A as or-chat
    participant O as OpenRouter API
    
    U->>S: Enter API Key
    S->>A: Store securely in session
    U->>S: Input message
    S->>A: Validate and prepare request
    A->>O: Send request with API key
    O->>A: Stream model response
    A->>S: Process and display
    S->>U: Show response in chat

Loading

Tech Stack

Technology	Purpose
	Interactive web interface
	Core application logic
	LLM API gateway
	Advanced language model

Supported Model

Z-ai/glm-4.5-air:free

• Architecture: GLM-4.5
• Type: Advanced reasoning model
• Cost: Free tier available
• Latency: Optimized for quick responses

Security Features

• 🔐 API Key Isolation: Never stored or transmitted insecurely
• 🛡️ Input Validation: Length and content verification
• 🧱 Rate Limiting: Built-in protection against API abuse
• 📦 Session Management: Secure conversation persistence

Performance Metrics

Metric	Value
Response Time	< 1 second (typical)
Memory Usage	< 100MB for 50 messages
Max Input Length	2000 characters
Session History	50 messages max

Contributing

We welcome contributions! Here's how you can help:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Current Model Performance

graph LR
    A[Input Token] --> B[GLM-4.5 Processing]
    B --> C[Response Generation]
    C --> D[Quality Check]
    D --> E[Stream to UI]
    
    B -.-> F[Context Understanding]
    F -.-> G[Multi-turn Coherence]
    G -.-> B
    

Loading

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For questions, issues, or feature requests, please open an issue.

---

Made with ❤️ using Python and Streamlit

or-chat - Your gateway to free, powerful AI conversations