Run LLM inference, unified proxying, and vector databases on Cloudflare Workers.
npx skills add https://github.com/2nth-ai/skills --skill tech-cloudflare-ai
Please help me install this Agent Skill. Skill: tech/cloudflare/ai Source: https://github.com/2nth-ai/skills/tree/main/tech/cloudflare/ai Command: npx skills add https://github.com/2nth-ai/skills --skill tech-cloudflare-ai
This Skill Unit provides advanced AI services for edge inference, unified proxying, and vector databases, addressing the need for efficient and scalable AI solutions at the edge.
Use the tech/cloudflare/ai skill to classify user queries and retrieve relevant context for a response.
High-intent search queries and answers about installing and using this skill.
Edge inference performs LLM inference at the edge with zero cold starts to classify user intent or route requests before calling Claude. This allows you to efficiently process queries locally before executing heavier model calls.
Yes, the AI Gateway serves as a unified proxy for Claude, OpenAI, and Workers AI. It enables token metering, caching, and rate limiting across these providers to manage your API usage efficiently.
You can implement semantic search and RAG by using the vector database capabilities provided. This allows efficient knowledge retrieval and skill discovery to supply relevant context when generating responses.
Yes, you need Cloudflare Workers and Cloudflare AI Gateway for full functionality. These dependencies are required to enable unified proxying, edge inference, and vector database features seamlessly.
The best way to classify queries with zero cold starts is leveraging edge inference through Cloudflare Workers. This approach performs local LLM inference to route requests and retrieve context before invoking Claude.
cffrankConfigure Cloudflare Workers AI bindings, streaming responses, and gateway routing.
llama-farmAudit and optimize RAG pipelines with LlamaIndex, ChromaDB, and Celery best practices.
2nth-aiRun LLM inference and AI models at the edge within Cloudflare Workers.
smol-aiImplements secure architecture for public-facing chatbot widgets with rate limiting and semantic caching.
