skills.rest
jhl-labs
jhl-labsOFFICIAL
Explore all skills by this author →
GitHub

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

50|Updated Nov 20, 2025
Search Tags:#embeddings#langchain#rag#electron#vector-search#retrieval-augmented-generation#document-search
One-click install
npx skills add https://github.com/jhl-labs/sepilot_desktop --skill rag-vector-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG & Vector Search
Source: https://github.com/jhl-labs/sepilot_desktop/tree/main/.claude/skills/rag-vector-search
Command: npx skills add https://github.com/jhl-labs/sepilot_desktop --skill rag-vector-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieves and augments LLM responses with relevant document context using RAG and vector search, reducing hallucinations and increasing accuracy.

Core Features & Use Cases

  • Embeddings-based retrieval and vector storage for fast, scalable context.
  • Document search and semantic retrieval across knowledge bases and corpora.
  • Use Case: Enhance customer support or research assistants by referencing pertinent documents during conversations.

Quick Start

Provide a retrieval-augmented answer by embedding the query, retrieving top relevant documents, and augmenting the prompt for the LLM.

Frequently Asked Questions about RAG & Vector Search

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

FAQPage Schema
How does retrieval-augmented generation reduce LLM hallucinations?▼

Retrieval-augmented generation reduces hallucinations by embedding the user query, retrieving relevant documents from a vector store, and injecting that context into the prompt to ground the LLM response in factual data.

How do I implement document search and semantic retrieval across a large corpus?▼

Implement semantic retrieval by generating embeddings for your corpus, storing them in a vector database, and executing vector search to fetch top relevant documents to augment your LLM prompts.

Can I use LangChain with vector search for knowledge-base enhancements?▼

Yes, you can use LangChain to integrate embeddings, vector storage, and retrieval logic, enabling knowledge-base enhancements and document search for your LLM applications.

What is the best way to augment LLM answers with relevant documents?▼

The best way to augment LLM answers is using RAG: embed the query, retrieve top relevant documents via vector search, and augment the prompt with the retrieved context before generation.

Do I need a vector store to build a retrieval-augmented generation pipeline?▼

Yes, a vector store is required to index embeddings and perform fast vector search, which is essential for retrieving relevant documents to augment LLM prompts in a RAG pipeline.

Why does my LLM response lack context from my knowledge base?▼

Your LLM lacks context because it is not using retrieval-augmented generation; embedding queries and retrieving documents via vector search injects the needed knowledge base context into the prompt.

Related Skills

Explore More Software Engineering Skills→
Yangel-hideYangel-hide

chroma

Store embeddings and metadata in an open-source vector database for semantic search.

Community
Advanced
nilecuinilecui
27

rag-implementation

Build RAG systems integrating vector databases and semantic search for LLM applications.

Community
Advanced
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
leonardoteodorooleonardoteodoroo

hybrid-search-implementation

Implement hybrid search combining vector similarity with keyword matching for RAG systems.

Community
Advanced