[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-e8db05fb-2ff5-433e-819c-8f7178c904a7":3,"$fUwYfqT1wyjjpEe3e9ciBStvKIps5A-Pl6MQ12s4lR2s":42},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":33},"e8db05fb-2ff5-433e-819c-8f7178c904a7","rag-implementation","RAG（检索增强生成）实现工作流程，涵盖嵌入选择、向量数据库设置、分块策略和检索优化。","cat_coding_backend","mod_coding","sickn33,coding","---\nname: rag-implementation\ndescription: \"RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.\"\ncategory: granular-workflow-bundle\nrisk: safe\nsource: personal\ndate_added: \"2026-02-27\"\n---\n\n# RAG Implementation Workflow\n\n## Overview\n\nSpecialized workflow for implementing RAG (Retrieval-Augmented Generation) systems including embedding model selection, vector database setup, chunking strategies, retrieval optimization, and evaluation.\n\n## When to Use This Workflow\n\nUse this workflow when:\n- Building RAG-powered applications\n- Implementing semantic search\n- Creating knowledge-grounded AI\n- Setting up document Q&A systems\n- Optimizing retrieval quality\n\n## Workflow Phases\n\n### Phase 1: Requirements Analysis\n\n#### Skills to Invoke\n- `ai-product` - AI product design\n- `rag-engineer` - RAG engineering\n\n#### Actions\n1. Define use case\n2. Identify data sources\n3. Set accuracy requirements\n4. Determine latency targets\n5. Plan evaluation metrics\n\n#### Copy-Paste Prompts\n```\nUse @ai-product to define RAG application requirements\n```\n\n### Phase 2: Embedding Selection\n\n#### Skills to Invoke\n- `embedding-strategies` - Embedding selection\n- `rag-engineer` - RAG patterns\n\n#### Actions\n1. Evaluate embedding models\n2. Test domain relevance\n3. Measure embedding quality\n4. Consider cost\u002Flatency\n5. Select model\n\n#### Copy-Paste Prompts\n```\nUse @embedding-strategies to select optimal embedding model\n```\n\n### Phase 3: Vector Database Setup\n\n#### Skills to Invoke\n- `vector-database-engineer` - Vector DB\n- `similarity-search-patterns` - Similarity search\n\n#### Actions\n1. Choose vector database\n2. Design schema\n3. Configure indexes\n4. Set up connection\n5. Test queries\n\n#### Copy-Paste Prompts\n```\nUse @vector-database-engineer to set up vector database\n```\n\n### Phase 4: Chunking Strategy\n\n#### Skills to Invoke\n- `rag-engineer` - Chunking strategies\n- `rag-implementation` - RAG implementation\n\n#### Actions\n1. Choose chunk size\n2. Implement chunking\n3. Add overlap handling\n4. Create metadata\n5. Test retrieval quality\n\n#### Copy-Paste Prompts\n```\nUse @rag-engineer to implement chunking strategy\n```\n\n### Phase 5: Retrieval Implementation\n\n#### Skills to Invoke\n- `similarity-search-patterns` - Similarity search\n- `hybrid-search-implementation` - Hybrid search\n\n#### Actions\n1. Implement vector search\n2. Add keyword search\n3. Configure hybrid search\n4. Set up reranking\n5. Optimize latency\n\n#### Copy-Paste Prompts\n```\nUse @similarity-search-patterns to implement retrieval\n```\n\n```\nUse @hybrid-search-implementation to add hybrid search\n```\n\n### Phase 6: LLM Integration\n\n#### Skills to Invoke\n- `llm-application-dev-ai-assistant` - LLM integration\n- `llm-application-dev-prompt-optimize` - Prompt optimization\n\n#### Actions\n1. Select LLM provider\n2. Design prompt template\n3. Implement context injection\n4. Add citation handling\n5. Test generation quality\n\n#### Copy-Paste Prompts\n```\nUse @llm-application-dev-ai-assistant to integrate LLM\n```\n\n### Phase 7: Caching\n\n#### Skills to Invoke\n- `prompt-caching` - Prompt caching\n- `rag-engineer` - RAG optimization\n\n#### Actions\n1. Implement response caching\n2. Set up embedding cache\n3. Configure TTL\n4. Add cache invalidation\n5. Monitor hit rates\n\n#### Copy-Paste Prompts\n```\nUse @prompt-caching to implement RAG caching\n```\n\n### Phase 8: Evaluation\n\n#### Skills to Invoke\n- `llm-evaluation` - LLM evaluation\n- `evaluation` - AI evaluation\n\n#### Actions\n1. Define evaluation metrics\n2. Create test dataset\n3. Measure retrieval accuracy\n4. Evaluate generation quality\n5. Iterate on improvements\n\n#### Copy-Paste Prompts\n```\nUse @llm-evaluation to evaluate RAG system\n```\n\n## RAG Architecture\n\n```\nUser Query -> Embedding -> Vector Search -> Retrieved Docs -> LLM -> Response\n                |              |              |              |\n            Model         Vector DB     Chunk Store    Prompt + Context\n```\n\n## Quality Gates\n\n- [ ] Embedding model selected\n- [ ] Vector DB configured\n- [ ] Chunking implemented\n- [ ] Retrieval working\n- [ ] LLM integrated\n- [ ] Evaluation passing\n\n## Related Workflow Bundles\n\n- `ai-ml` - AI\u002FML development\n- `ai-agent-development` - AI agents\n- `database` - Vector databases\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,82,1700,"2026-05-16 13:36:15",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"编程开发","coding","mdi-code-braces","代码生成、调试、审查，提升开发效率",2,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":25,"skillCount":32,"createdAt":26},"后端开发","backend","mdi-server","API、数据库、服务端架构",296,[34],{"id":35,"skillId":4,"version":36,"fileName":37,"fileSize":38,"filePath":39,"fileHash":40,"manifest":41,"createdAt":19},"69560102-c251-49dc-b813-9f4840eccbfa","1.0.0","rag-implementation.zip",1725,"uploads\u002Fskills\u002Fe8db05fb-2ff5-433e-819c-8f7178c904a7\u002Frag-implementation.zip","2f65b34e72e013b688add39a090f0f30af8d25fd5ce2aafbf34b80aec4c77521","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":4603}]",{"code":43,"message":44,"data":45},200,"success",{"items":46,"stats":47,"page":50},[],{"averageRating":48,"totalRatings":48,"ratingCounts":49},0,[48,48,48,48,48],{"limit":51,"offset":48,"hasMore":52,"nextOffset":51,"ratedOnly":16},15,false]