An open-source AI chatbot app template built with Next.js, the Vercel AI SDK, OpenAI, and Vercel KV. This chatbot utilises RAG and vector database to provide information on government policies and regulations.
Features · Our Architecture · Chat Page · Other authors
- Next.js App Router
- React Server Components (RSCs), Suspense, and Server Actions
- Vercel AI SDK for streaming chat UI
- Support for OpenAI (default), Anthropic, Cohere, Hugging Face, or custom AI chat models and/or LangChain
- shadcn/ui
- Styling with Tailwind CSS
- Radix UI for headless component primitives
- Icons from Phosphor Icons
- Chat History, rate limiting, and session storage with Vercel KV
- NextAuth.js for authentication
This project make use of LLM with LangChain to provide information on government policies and regulations. It also uses Retrieval Augmented Generation (RAG) and vector database from Supabase instance to reduce the search space for the LLM model and provide more accurate results.
Starting a business is difficult enough, the huge suite of government programs is also not easy to navigate. How can we make a simple-to-use, intelligent G2B digital system that brings businesses closer to government support?
This product can:
- Understand the needs and concerns of the business
- Classify the needs and concerns of the business
- Serve targeted programs and schemes that businesses will benefit from
Here is an example of the chat page. The chat page is designed to be simple and easy to use. The chatbot will provide information on government policies and regulations based on the user's input.
This library is created by Vercel and Next.js team members, with contributions from: