cf-ai

What problem does it solve?

This Skill simplifies the deployment of AI models and applications directly on Cloudflare's edge network, enabling low-latency inference, efficient data processing, and robust AI-powered features.

Core Features & Use Cases

• Edge AI Inference: Run models like Llama 3, Stable Diffusion, and Whisper directly on Cloudflare Workers.
• Vector Databases: Integrate with Vectorize for building RAG pipelines and similarity search.
• AI Gateway: Proxy and manage AI provider requests with caching, rate limiting, and fallbacks.
• RAG Pipelines: Build Retrieval Augmented Generation systems using Vectorize, D1, and Workers AI.

Quick Start

Use the cf-ai skill to generate a Cloudflare Worker configuration for text generation using the Llama 3 model.