Skip to content
Log InContact
Sign Up

Vezlo AI Assistant Server

Overview

Deploy the Vezlo AI Assistant Server — a production-ready Node.js backend with RAG-based knowledge base, vector embeddings, and conversational APIs.

Part of the complete Vezlo AI ecosystem that transforms your codebase into an intelligent chatbot. The Assistant Server provides core backend infrastructure with RESTful APIs for conversation management, real-time WebSocket communication, and semantic search powered by Supabase.

Works seamlessly with src-to-kb (code analysis) and assistant-chat (widget/dashboard) to create AI assistants that understand your codebase.

Preview
Instructions

Once you connect this integration, select your Vercel project and provide your Supabase credentials, OpenAI API key, and database connection details during the installation process. The Assistant Server will be deployed and running in the background automatically.

After successful deployment, you'll be presented with a migration URL in the following format: https://your-project.vercel.app/api/migrate?key=YOUR_MIGRATION_SECRET

Important: Run this migration URL once after deployment. This will automatically create all required database tables and schema in your Supabase instance. Once the migration is completed successfully, your Assistant Server is ready use.

You can verify the deployment by accessing:

  • Health check: https://your-project.vercel.app/health
  • API documentation: https://your-project.vercel.app/docs

For complete documentation, API reference, and integration guides, visit the Assistant Server GitHub Repository