RAG Implementation Skill ðŸ§
CommunityBuild 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. Covers Pinecone, Weaviate, Chroma, embeddings, retrieval strategies, reranking, and hybrid search.
How to Use This Skill
- Click "View SKILL.md" to see the full skill definition
- Copy the contents of the SKILL.md file
- In Claude, go to Project Knowledge and paste the skill
- Start a new conversation and Claude will use the skill automatically
Leave a Comment
Related Skills
Google ADK Python
CommunityExpert guide for Google's Agent Development Kit (ADK) Python for building AI agents
AI & Machine Learningby mrgoonie
agentsgoogleadk
Prompt Engineering Patterns
CommunityMaster advanced prompt engineering techniques to maximize LLM performance and reliability
AI & Machine Learningby wshobson
promptsllmoptimization
Embedding Strategies
CommunitySelect and optimize embedding models for semantic search and RAG applications
AI & Machine Learningby wshobson
embeddingsragvector