OpenAI Cookbook

Most code examples are written in Python, though the concepts can be applied in any language.

课时

• .codex
  • skills
    • docs-editor
      • resources
        • OpenAI Cookbook editorial checklist
      • OpenAI Cookbook docs editor
• .github
  • pull request template
• articles
  • Building workspace agents in ChatGPT to complete repeatable, end-to-end work
  • Using PLANS.md for multi-hour problem solving
  • User guide for gpt-oss-safeguard
  • gpt-oss
    • How to handle the raw chain of thought in gpt-oss
    • How to run gpt-oss locally with LM Studio
    • How to run gpt-oss locally with Ollama
    • How to run gpt-oss with Hugging Face Transformers
    • How to run gpt-oss with vLLM
    • Verifying gpt-oss implementations
  • How to work with large language models
  • OpenAI harmony response format
  • Build a per-run spending controller with the Responses API
  • Related resources from around the web
  • Techniques to improve reliability
  • Text comparison examples
  • What’s new with DALL·E-3?
  • What makes documentation good
• examples
  • agents_sdk
    • deployment_manager
      • Agents SDK Deployment Manager
    • migrate-from-claude-agent-sdk
      • Migrate from the Claude Agent SDK to the OpenAI Agents SDK
    • multi-agent-portfolio-collaboration
      • prompts
        • Code Interpreter Prompt (Best Practices, GPT-4.1)
        • Memo Editor – Prompt
        • Lead Fundamental Analyst – Prompt
        • Macro Strategist – Prompt
        • Portfolio Manager – System Prompt
        • Quantitative Researcher – Prompt
        • Tool Call Retry Instructions
    • sandboxed-code-migration
      • repo_fixtures
        • case_summary_service
          • Migration request: Chat Completions to Responses
          • Case summary service
        • support_reply_service
          • Migration request: Chat Completions to Responses
          • Customer Support Reply Bot
  • audio
    • duplex_voice_agent_evaluation
      • assistants
        • client
          • Application-managed client delegation
        • frontend
          • Shared GPT Live frontend
        • Evaluated assistant
        • responses
          • OpenAI-managed Responses delegation
      • crawl_harness
        • Crawl harness
      • docs
        • Interaction metric contract v2
      • Evaluating full-duplex voice agents
      • recorded-example
        • Recorded example: John / Cedar / GPT Live
      • run_harness
        • Run harness
      • shared
        • Shared evaluation infrastructure
      • walk_harness
        • Walk harness
    • GPT-Live evaluation guide
  • How to build an agent with the Node.js SDK

开始学习 → OpenAI Cookbook editorial checklist