Spaces:
Runtime error
Runtime error
A newer version of the Gradio SDK is available:
6.1.0
Deployment Guides
This directory contains deployment guides for different cloud platforms.
Available Guides
- Nebius Deployment - Complete guide for deploying to Nebius cloud platform
Quick Reference
Current Setup (Modal)
- RAG inference: Modal GPU containers
- Vector DB: Remote ChromaDB on Modal
- Web app: Local Flask server
Nebius Deployment
- RAG inference: Nebius GPU VM/Container
- Vector DB: Local ChromaDB or managed service
- Web app: Nebius VM or container
Migration Path
- Read the deployment guide for your target platform
- Create standalone RAG service (remove Modal dependencies)
- Update web app to use HTTP API instead of Modal CLI
- Deploy infrastructure (VM/containers)
- Index documents in new environment
- Test end-to-end
- Switch traffic from Modal to new platform
Support
For deployment issues, see:
- Platform-specific deployment guide
docs/guides/TROUBLESHOOTING.md- Project README.md