AI AI AI
Workers AI Workers AI Workers AI
Workers AI chạy inference (LLM/embeddings/vision) trên Cloudflare và tích hợp qua binding. Model inference (LLM, embedding, vision) qua binding Workers — trả tiền theo usage, chạy gần user. Workers AI runs inference (LLMs/embeddings/vision) on Cloudflare and integrates via bindings. Model inference (LLM, embeddings, vision) via Workers bindings — pay per use, runs near users. Workers AI runs inference (LLMs/embeddings/vision) on Cloudflare and integrates via bindings. Model inference (LLM, embeddings, vision) via Workers bindings — pay per use, runs near users.
Là gì? What is it? What is it?
Workers AI chạy inference (LLM/embeddings/vision) trên Cloudflare và tích hợp qua binding. Model inference (LLM, embedding, vision) qua binding Workers — trả tiền theo usage, chạy gần user. Workers AI runs inference (LLMs/embeddings/vision) on Cloudflare and integrates via bindings. Model inference (LLM, embeddings, vision) via Workers bindings — pay per use, runs near users. Workers AI runs inference (LLMs/embeddings/vision) on Cloudflare and integrates via bindings. Model inference (LLM, embeddings, vision) via Workers bindings — pay per use, runs near users.
Tại sao quan trọng? Why it matters ហេតុអ្វីសំខាន់
Thêm AI vào app mà không tự host GPU — inference và RAG chạy trên mạng Cloudflare. Add AI to apps without hosting GPUs — inference and RAG run on Cloudflare’s network. Add AI to apps without hosting GPUs — inference and RAG run on Cloudflare’s network.
Khi nào nên dùng? When to use it When to use it
- Khi bạn cần giải pháp Workers AI trên Cloudflare thay vì tự host When you need Workers AI on Cloudflare instead of self-hosting When you need Workers AI on Cloudflare instead of self-hosting
- Khi team mới bắt đầu và muốn bản free/low-ops để thử When your team is starting out and wants a low-ops free tier to experiment When your team is starting out and wants a low-ops free tier to experiment
- Khi tài liệu chính thức gợi ý sản phẩm này cho use case của bạn When official docs recommend this product for your use case When official docs recommend this product for your use case
Ví dụ đơn giản Simple example Simple example
Ví dụ: một team SME bật Workers AI cho website onboarding — họ thấy lợi ích ngay mà chưa cần kiến trúc phức tạp. Example: an SME team enables Workers AI for an onboarding site — they see value quickly without a complex architecture. Example: an SME team enables Workers AI for an onboarding site — they see value quickly without a complex architecture.
Đừng nhầm Workers AI với toàn bộ nền tảng Cloudflare — đây là một mảnh ghép; kết hợp với DNS/proxy và sản phẩm liên quan. Don’t confuse Workers AI with the entire Cloudflare platform — it’s one piece; combine it with DNS/proxy and related products. Don’t confuse Workers AI with the entire Cloudflare platform — it’s one piece; combine it with DNS/proxy and related products.
Hình ảnh trực quan (Cloudflare Docs) Visual guides (Cloudflare Docs) Visual guides (Cloudflare Docs)
Kiến trúc AI kết hợp (composable) Composable AI architecture Composable AI architecture
Ứng dụng AI có thể dựng end-to-end trên Cloudflare, hoặc gắn từng dịch vụ vào hạ tầng và dịch vụ bên ngoài. The architecture diagram illustrates how AI applications can be built end-to-end on Cloudflare, or single services can be integrated with external infrastructure and services. The architecture diagram illustrates how AI applications can be built end-to-end on Cloudflare, or single services can be integrated with external infrastructure and services.
Thuật ngữ: Concepts: Concepts: Workers AI · AI Gateway · External LLM · Composable stack
Sơ đồ chính thức ↗ Official diagram ↗ Official diagram ↗ · AI Artificial Intelligence (AI) Artificial Intelligence (AI)
Retrieval Augmented Generation (RAG) Retrieval Augmented Generation (RAG) Retrieval Augmented Generation (RAG)
RAG kết hợp retrieval (Vectorize/KV) với Workers AI để chatbot trả lời chính xác hơn — seeding knowledge và query path tách biệt. RAG combines retrieval with generative models for better text. It uses external knowledge to create factual, relevant responses, improving coherence and accuracy in NLP tasks like chatbots. RAG combines retrieval with generative models for better text. It uses external knowledge to create factual, relevant responses, improving coherence and accuracy in NLP tasks like chatbots.
Thuật ngữ: Concepts: Concepts: RAG · Vectorize · Workers AI · Knowledge seeding · Embeddings
Sơ đồ chính thức ↗ Official diagram ↗ Official diagram ↗ · AI Artificial Intelligence (AI) Artificial Intelligence (AI)
Sản phẩm liên quan Related products Related products
- Vectorize Vectorize Vectorize
Vectorize là vector database để làm semantic search/RAG trên nội dung học. Vector database cho RAG / semantic search — lưu embedding, query từ Workers AI hoặc model ngoài. Vectorize is a vector database for semantic search/RAG over your learning content. Vector database for RAG / semantic search — store embeddings, query from Workers AI or external models. Vectorize is a vector database for semantic search/RAG over your learning content. Vector database for RAG / semantic search — store embeddings, query from Workers AI or external models.
- AI Gateway AI Gateway AI Gateway
AI Gateway giúp quản trị calls tới AI providers (routing, caching, observability, cost). Lớp quản trị request tới nhiều provider (OpenAI, Anthropic, …): cache, log, rate limit, chi phí. AI Gateway governs AI calls (routing, caching, observability, cost). Govern requests to multiple providers (OpenAI, Anthropic, …): cache, logs, rate limits, cost. AI Gateway governs AI calls (routing, caching, observability, cost). Govern requests to multiple providers (OpenAI, Anthropic, …): cache, logs, rate limits, cost.
Tiếp theo Next step Next step
Quay lại bản đồ sản phẩm hoặc chọn lộ trình học phù hợp. Return to the product map or pick a learning track. Return to the product map or pick a learning track.