rag-search

Name: rag-search
Availability: InStock
Author: moongci38-oss

Perform semantic and hybrid vector plus BM25 search on document collections.

Updated Jun 3, 2026

Search Tags:#semantic search #information retrieval #vector search #document search #BM25 search

Ready to run

npx skills add https://github.com/moongci38-oss/forge-plugins --skill rag-search-moongci38-oss

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-search
Source: https://github.com/moongci38-oss/forge-plugins/tree/main/forge-core/skills/rag-search
Command: npx skills add https://github.com/moongci38-oss/forge-plugins --skill rag-search-moongci38-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires llama-index, faiss-cpu, bm25retriever, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of finding relevant documents based on meaning rather than exact keywords, making it easier to find the information you need, even when you're not sure exactly what you're looking for.

Core Features & Use Cases

Semantic Search: Perform searches based on the meaning of keywords, not just the exact words.
Hybrid Search: Combines vector-based and BM25 search for improved accuracy.
Use Case: Imagine you're writing a policy document and need to find examples of similar policies from past years. Use this Skill to find documents that match the meaning, not just the exact words, of your search query.

Quick Start

Use the /rag-search command followed by your search query, e.g., /rag-search "policy framework".

Frequently Asked Questions about rag-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform semantic search on documents to find meaning instead of exact keywords?▼

Semantic search on documents finds relevant information based on meaning rather than exact keywords. This Skill uses LlamaIndex and FAISS to index document collections and retrieve contextually relevant results for research and policy writing workflows.

Can I combine vector search and BM25 search for document retrieval?▼

Yes, you can combine vector search and BM25 search for document retrieval through hybrid search. This approach merges vector-based semantic matching with BM25 keyword search to improve accuracy and relevance ranking across document collections.

What's the best way to start running semantic search queries on my document collections?▼

The best way to start running semantic search queries is using the /rag-search command followed by your query text. This triggers the hybrid retrieval pipeline to load your documents via LlamaIndex and return meaning-based matches.

Do I need LlamaIndex and FAISS installed to use this hybrid search approach?▼

Yes, you need LlamaIndex and FAISS installed to use this hybrid search approach. LlamaIndex handles document loading and indexing, FAISS provides vector storage, and BM25Retriever executes keyword search to complete the pipeline.

Does BM25Retriever work with FAISS vector storage for information retrieval?▼

BM25Retriever works with FAISS vector storage for information retrieval by running parallel queries. The hybrid mechanism merges semantic vector results from FAISS with keyword-based BM25 results to optimize meaning-based relevance.

When should I not use semantic search for document analysis?▼

You should not use semantic search for document analysis when you need exact string matching or strict keyword filtering. Semantic search optimizes for meaning-based relevance, which may bypass exact phrases required for compliance or legal document review.