rag-and-vector-search
Use when building RAG systems, implementing semantic/hybrid search, selecting vector databases, tuning retrieval quality, or choosing chunking and embedding strategies.
npx skills add majiayu000/claude-skill-registry --skill rag-and-vector-search --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# RAG and Vector Search ## Embedding Model Selection | Model | Dims | Best For | |-------|------|----------| | text-embedding-3-large | 3072 | Highest accuracy (OpenAI); supports Matryoshka dim reduction | | text-embedding-3-small | 1536 | Cost-effective default (OpenAI) | | voyage-3 | 1024 | Code, legal, finance domains (best retrieval quality) | | gte-Qwen2-7B-instruct | 3584 | Best open-source; instruction-tuned | | bge-large-en-v1.5 | 1024 | Strong open-source English, smaller footprint | | all-MiniLM-L6-v2 | 384 | Fast/lightweight, prototyping | | multilingual-e5-large | 1024 | Multi-language (requires query/passage prefixes) | ### Matryoshka Embeddings Models like text-embedding-3-large support dimension reduction: truncate vectors to 256/512/1024 dims with minimal quality loss. Reduces storage 3-12x. Test recall at target dimension before committing. **Never mix embedding models** in the same index -- vectors from different models are incompatible. ## Chunking Decisions | Strategy | When | |----------|------| | Token-based (512-1000) | Default; predictable size | | Semantic/header-based | Markdown/structured docs; preserves logical units | | Recursive character | Unstructure
- Embedding Model Selection
- Matryoshka Embeddings
- Chunking Decisions
- Distance Metrics
- Index Selection by Scale
- HNSW Tuning
- Vector Database Selection
- Retrieval Architecture
- Hybrid Search (Preferred for Production)
- Reranking (Always Worth It)
- pgvector + FTS Pattern
- Advanced RAG Patterns
- GraphRAG
- Contextual Retrieval (Anthropic Pattern)
What does the rag-and-vector-search skill do?
Use when building RAG systems, implementing semantic/hybrid search, selecting vector databases, tuning retrieval quality, or choosing chunking and embedding strategies.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill rag-and-vector-search --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.