Cerch Ai

Chat SDK is a free, open-source template built with Next.js and the AI SDK that helps you quickly build powerful chatbot applications.

Read Docs · Features · Model Providers · Running locally

Features

• Next.js App Router
  • Advanced routing for seamless navigation and performance
  • React Server Components (RSCs) and Server Actions for server-side rendering and increased performance
• AI SDK
  • Unified API for generating text, structured objects, and tool calls with LLMs
  • Hooks for building dynamic chat and generative user interfaces
  • Supports xAI (default), OpenAI, Fireworks, and other model providers
• shadcn/ui
  • Styling with Tailwind CSS
  • Component primitives from Radix UI for accessibility and flexibility
• Data Persistence
  • Neon Serverless Postgres for saving chat history and user data
  • Vercel Blob for efficient file storage
• Auth.js
  • Simple and secure authentication

Model Providers

This template ships with OpenAI gpt-4o-mini as the default chat model. However, with the AI SDK, you can switch LLM providers to Anthropic, Cohere, and many more with just a few lines of code.

In the chat header you can enter your own OpenAI API key, which will be used for chat responses and artifact generation.

Running locally

You will need to use the environment variables defined in .env.example to run Next.js AI Chatbot. It's recommended you use Vercel Environment Variables for this, but a .env file is all that is necessary.

Note: You should not commit your .env file or it will expose secrets that will allow others to control access to your various AI and authentication provider accounts.

1. Install Vercel CLI: npm i -g vercel
2. Link local instance with Vercel and GitHub accounts (creates .vercel directory): vercel link
3. Download your environment variables: vercel env pull

pnpm install
pnpm dev

Your app template should now be running on localhost:3000.

Webset artifact

The webset artifact focuses on people and company profiles. It renders CSV data in a sleek, responsive table with search, per-column filters, sorting, column visibility, sticky headers, and CSV export. Recommended columns include: name, title, company, industry, website/company_url, linkedin_url, location, size, funding, description.

LLM Flow (GPT-5)

• Provider: lib/ai/providers.ts maps logical model ids to OpenAI models. chat-model, artifact-model, and title-model use gpt-5; chat-model-reasoning uses gpt-5-reasoning with reasoning traces extracted via <think> tags.
• System prompts: lib/ai/prompts.ts selects prompts per model. Non-reasoning chat includes the Artifacts instructions so GPT-5 knows when/how to call tools.
• Tools/Artifacts: app/(chat)/api/chat/route.ts wires tools for weather, document create/update, suggestions, Gmail. Artifact servers in artifacts/*/server.ts stream typed outputs (text/code/sheet/webset) to the UI.
• API key: Users set an OpenAI API key in Settings overlay (stored as openai-api-key cookie). If empty, OPENAI_API_KEY env var is used.
• Model selection: UI exposes a model selector (components/model-selector.tsx) constrained by entitlements. Selection is stored as chat-model cookie and used by the chat API.