AI Chat with Convex Vector Search

An example of building AI-powered chat interface using Convex vector search.

Overview:

This app demonstrates how you can add a chat bot to an existing website, powered by Convex.

• The chat is trigged by a button in App.tsx
• The chat frontend is all in src/aiChat
• An example of web scraping is in convex/ingest/load.ts
• Embedding is performed in convex/ingest/embed.ts
• The public endpoints for the backend are in convex/messages.ts
• The answering logic is in convex/serve.ts

Running the App

npm install
npm run dev

This will configure a Convex project if you don't already have one, open the Convex dashboard and the web app running on localhost.

For the chat itself to work, you must configure the following environment variable on the Convex dashboard:

• OPEN_API_KEY set to an OpenAI API key (should start with sk-)

You can change the LLM identifier OPENAI_MODEL in convex/serve.ts to "gpt-4-32k" if you're paying for OpenAI to improve the quality of responses.

What is Convex?

Convex is a hosted backend platform with a built-in database that lets you write your database schema and server functions in TypeScript. Server-side database queries automatically cache and subscribe to data, powering a realtime useQuery hook in our React client. There are also Python, Rust, ReactNative, and Node clients, as well as a straightforward HTTP API.

The database support NoSQL-style documents with relationships and custom indexes (including on fields in nested objects).

The query and mutation server functions have transactional, low latency access to the database and leverage our v8 runtime with determinism guardrails to provide the strongest ACID guarantees on the market: immediate consistency, serializable isolation, and automatic conflict resolution via optimistic multi-version concurrency control (OCC / MVCC).

The action server functions have access to external APIs and enable other side-effects and non-determinism in either our optimized v8 runtime or a more flexible node runtime.

Functions can run in the background via scheduling and cron jobs.

Development is cloud-first, with hot reloads for server function editing via the CLI. There is a dashbord UI to browse and edit data, edit environment variables, view logs, run server functions, and more.

There are built-in features for reactive pagination, file storage, reactive search, https endpoints (for webhooks), streaming import/export, and runtime data validation for function arguments and database data.

Everything scales automatically, and it’s free to start.