跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Rag Implementation

技能 已验证 活跃

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

目的

Build sophisticated Retrieval-Augmented Generation (RAG) systems for LLM applications, enabling knowledge-grounded AI with vector databases and semantic search.

功能

  • Build RAG systems
  • Integrate vector databases
  • Implement semantic search
  • Reduce LLM hallucinations
  • Use various embedding models

使用场景

  • Building Q&A systems over proprietary documents
  • Creating chatbots with current, factual information
  • Implementing semantic search with natural language queries
  • Enabling LLMs to access domain-specific knowledge

非目标

  • This skill does not provide a ready-to-run RAG system, but rather guidance and implementation patterns.
  • It does not abstract away the complexities of vector database management or embedding model selection entirely.

安装

请先添加 Marketplace

/plugin marketplace add wshobson/agents
/plugin install llm-application-dev@claude-code-workflows

质量评分

已验证
98 /100
1 day ago 分析

信任信号

最近提交3 days ago
星标35.3k
许可证MIT
状态
查看源代码