Profile My skills Saved Collections Edit profile Submit a skill

Smart Search

Use this for hybrid Vector+BM25 search to find specific existing info in the knowledge base—use only for factual, pre-existing content (skip guidance on creating/structuring docs, formatting, external queries, or search method questions)

chainlesschain 8a82a6d 2 files · 6.2 KB Updated
Web & Frontend

File contents

Smart Search Skill

Search across your knowledge base using hybrid Vector+BM25 search.

Usage

/smart-search <query>
/smart-search similar <document_reference>

Search Modes

Mode Description
search (default) Hybrid search combining semantic and keyword matching
similar Find documents similar to a reference
vector Pure semantic/vector search
keyword Pure BM25 keyword search

How It Works

  1. Hybrid Search (default): Combines vector similarity (60% weight) with BM25 keyword matching (40% weight) using Reciprocal Rank Fusion
  2. Vector Search: Uses RAG embeddings for semantic similarity
  3. BM25 Search: Okapi BM25 algorithm with Chinese/English tokenizer
  4. Performance: <20ms search latency with parallel execution

chainlesschain/chainlesschain/tree/main/desktop-app-vue/src/main/ai-engine/cowork/skills/builtin/smart-search commit 8a82a6d10e

Browse category

Frequently asked questions

npx skillmds@latest add chainlesschain/smart-search