Download
SearChat is an open-source conversational search platform that combines traditional web search engines with large language model reasoning to create an interactive research environment. The project is designed to transform the process of web searching into a multi-turn conversational experience where users can refine queries and explore results through dialogue. Built using a modern monorepo architecture, the system includes a Node.js and Koa backend alongside a Vue 3 and TypeScript frontend that delivers a responsive chat interface. The platform supports multiple AI providers, allowing developers to connect models from providers such as OpenAI, Anthropic, or Google Gemini to generate contextual responses. It can integrate with several search engines including Bing, Google, and SearXNG to retrieve external information that the language model then analyzes and summarizes.
Features
- Conversational search interface that allows multi-turn dialogue with search results
- Integration with multiple search engines including Bing, Google, and SearXNG
- Support for multiple large language model providers such as OpenAI, Gemini, and Anthropic
- Deep research mode capable of iterative information gathering and report generation
- Modular architecture combining Node.js backend with Vue and TypeScript frontend
Project Samples
