Awesome AI Resources
这里收录适合 AI 应用工程师持续学习的高质量资源。原则是少而精,优先选择官方文档、经典教程和真实工程案例。
学习顺序建议
新手不要一开始就打开几十个链接。建议按这个顺序:
- 先读模型平台官方文档,知道 API 怎么用。
- 再读 RAG 和 Agent 框架文档,知道常见架构。
- 做项目时查向量数据库、部署和评测工具。
- 遇到具体问题再看论文和深度文章。
官方文档
- OpenAI Platform Docs: https://platform.openai.com/docs
- Anthropic Docs: https://docs.anthropic.com
- Google AI for Developers: https://ai.google.dev
- Model Context Protocol: https://modelcontextprotocol.io
- LangChain Docs: https://python.langchain.com/docs
- LlamaIndex Docs: https://docs.llamaindex.ai
模型平台
- OpenAI: https://platform.openai.com
- Anthropic: https://console.anthropic.com
- Google AI Studio: https://aistudio.google.com
- Groq: https://console.groq.com
- Together AI: https://www.together.ai
- Fireworks AI: https://fireworks.ai
RAG
- LlamaIndex RAG Guide: https://docs.llamaindex.ai
- LangChain RAG Tutorials: https://python.langchain.com/docs/tutorials/rag
- Qdrant Docs: https://qdrant.tech/documentation
- pgvector: https://github.com/pgvector/pgvector
- Milvus: https://milvus.io/docs
- Weaviate: https://weaviate.io/developers/weaviate
- Chroma: https://docs.trychroma.com
Agent
- OpenAI Agents SDK: https://openai.github.io/openai-agents-python
- LangGraph: https://langchain-ai.github.io/langgraph
- AutoGen: https://microsoft.github.io/autogen
- CrewAI: https://docs.crewai.com
MCP
- MCP Official Site: https://modelcontextprotocol.io
- MCP Specification: https://modelcontextprotocol.io/specification
- MCP Servers: https://github.com/modelcontextprotocol/servers
Evaluation
- OpenAI Evals: https://github.com/openai/evals
- Ragas: https://docs.ragas.io
- DeepEval: https://docs.confident-ai.com
- LangSmith: https://docs.smith.langchain.com
Document Processing
- MarkItDown: https://github.com/microsoft/markitdown
- Unstructured: https://docs.unstructured.io
- PyMuPDF: https://pymupdf.readthedocs.io
- Docling: https://github.com/docling-project/docling
Engineering
- FastAPI: https://fastapi.tiangolo.com
- Next.js: https://nextjs.org/docs
- Docker: https://docs.docker.com
- PostgreSQL: https://www.postgresql.org/docs
- Redis: https://redis.io/docs
- Vercel: https://vercel.com/docs
AI Coding
- GitHub Copilot: https://docs.github.com/copilot
- Cursor: https://docs.cursor.com
- Continue: https://docs.continue.dev
推荐筛选标准
加入资源前请确认:
- 是否仍在维护
- 是否有清晰示例
- 是否适合中文开发者学习
- 是否能帮助完成真实项目
- 是否避免标题党和低质量搬运
不建议新手一开始深挖的内容
- 大模型预训练细节
- 分布式训练优化
- CUDA 底层性能调优
- 复杂多 Agent 理论
- 追逐所有新框架
这些内容不是不重要,而是对“先做出 AI 应用”来说优先级没那么高。