Promptie

A tool for testing prompts and generations with Ragie. This is a Next.js application that allows you to experiment with AI text generation using the Ragie knowledge retrieval system and Anthropic's Claude AI.

Features

• Interactive prompt testing interface
• System prompt customization
• Knowledge retrieval with Ragie
• Response generation with Anthropic AI or OpenRouter
• Citation support for retrieved information
• Configurable parameters (partition, topK, rerank)
• Configurable LLM provider (Anthropic or OpenRouter)

Prerequisites

• Node.js 18.x or higher
• npm or yarn
• Ragie API key (Get one at https://secure.ragie.ai)
• Anthropic API key (if using Anthropic as the LLM provider)
• OpenRouter API key (if using OpenRouter as the LLM provider, get one at https://openrouter.ai/)

Installation

1. Clone the repository

git clone https://github.com/yourusername/promptie.git
cd promptie

2. Install dependencies

npm install
# or
yarn install

3. Set up environment variables

   • Create a .env file in the root directory by copying .env.example.
   • Add your API keys and configure the LLM provider as shown below. Refer to the comments in the .env.example file for more details.

   # Your Ragie API key (Get one at https://secure.ragie.ai)
   RAGIE_API_KEY=your_ragie_api_key_here
   
   # ANTHROPIC_API_KEY: Your Anthropic API key.
   # Get one from https://www.anthropic.com/
   ANTHROPIC_API_KEY=your_anthropic_api_key_here
   
   # OPENROUTER_API_KEY: Your OpenRouter API key.
   # Get one from https://openrouter.ai/
   OPENROUTER_API_KEY=your_openrouter_api_key_here
   # required for the frontend to detect OpenRouter support and show relevant UI:
   NEXT_PUBLIC_OPENROUTER_API_KEY=$OPENROUTER_API_KEY

Development

Start the development server:

npm run dev
# or
yarn dev

The application will be available at http://localhost:3000.

Usage

1. Enter your message in the input field
2. Configure parameters as needed:
   • Partition: Set knowledge partition (default: "default")
   • Top K: Number of results to retrieve (default: 6)
   • Rerank: Toggle to enable/disable result reranking
3. Click "Send" to generate a response
4. View the generated text and citations

Building for Production

Build the application for production:

npm run build
# or
yarn build

Start the production server:

npm run start
# or
yarn start

Technologies

• Next.js - React framework
• LLM Providers:
  • Anthropic Claude - AI assistant
  • OpenRouter - Access various LLMs via a single API
• Ragie - Knowledge retrieval system
• Tailwind CSS - Utility-first CSS framework
• TypeScript - Type safety

License

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