Context Engineering（Bonigarcia 教程）
Context engineering can be defined as the practice of designing systems that provide a Large Language Model (LLM) and AI agents with all the necessary information to complete a task effectively. It goes beyond prompt engineering since it focuses on building a comprehensive and structured context from various…
课时
- Examples
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- project-notetaker
- task-tracker
- OpenAI (Python)
- LangChain
- System prompt (Python)
- Python
- Python
- workspace-analyzer
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- Python
- LLMLingua
- OpenViking
- CrewAI
- LangGraph
- DeepAgents
- Python
- DeepEval
- Promptfoo
- Ragas
- Langfuse
- LangSmith
- Microsoft Presidio
- Pydantic
- Fairlearn
- LiteLLM
- Python
- Python
- Python
- LangChain
- LangGraph
- ch01
- Basic interaction with LLMs in Java
- Basic interaction with LLMs in JavaScript
- Basic interaction with Anthropic Claude models
- Streaming responses from Anthropic Claude models
- Basic interaction with Google Gemini models
- Streaming responses from Google Gemini models
- Basic interaction with a local LLM using Ollama
- Streaming responses from a local LLM using Ollama
- Basic interaction with OpenAI GPT models
- Streaming responses from OpenAI GPT models
- Basic interaction with LLMs in Jupyter Notebooks
- Basic interaction with LLMs in Python
- ch02
- ch03
- ch04
- ch05
- ch06
- ch10
- Agent Development Kit (ADK) examples
- Microsoft Agent Framework examples
- Agno examples
- Vercel AI SDK examples
- Amazon Bedrock AgentCore examples
- Claude Agent SDK examples
- CrewAI examples
- DeepAgents examples
- DSPy examples
- Embabel examples
- Gemini Enterprise Agent Platform examples
- Haystack examples
- langchain
- LangChain4j examples
- langgraph
- LlamaIndex examples
- n8n workflow examples
- OpenClaw examples