skills.rest
qcmuu
qcmuuCOMMUNITY
Explore all skills by this author →
GitHub

llamaindex

Build RAG applications that answer questions over documents using LlamaIndex.

Updated May 2, 2026
Search Tags:#rag#multimodal#agents#retrieval#document ingestion#query engine#vector indexing
One-click install
npx skills add https://github.com/qcmuu/AI-Research-Skills --skill llamaindex-qcmuu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/qcmuu/AI-Research-Skills/tree/main/14-agents/llamaindex
Command: npx skills add https://github.com/qcmuu/AI-Research-Skills --skill llamaindex-qcmuu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

LlamaIndex removes the complexity of turning your private documents into a retrieval-augmented generation (RAG) system that can answer questions and support chat over knowledge you control.

Core Features & Use Cases

  • Ingest data with connectors (300+ options): Load documents from local folders, web pages, GitHub, databases, and many third-party sources.
  • Index your content for retrieval: Create vector, list, and tree indexes and persist them to avoid re-indexing.
  • Query and agent workflows: Use query engines for response generation, retrievers for chunk selection, and RAG agents that decide when to search and when to use tools.
  • Multimodal + evaluation hooks: Support multi-modal RAG patterns and evaluate response quality (e.g., relevance and faithfulness).

Quick Start

Tell your AI coding agent: "Use LlamaIndex to load documents from the 'data' folder, build a vector index, persist it to disk, and answer the question: 'What did the author do growing up?'"

Frequently Asked Questions about llamaindex

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

FAQPage Schema
How do I build a RAG system over my private documents?▼

Build a RAG system by using LlamaIndex to ingest documents from local folders or web pages, create vector indexes, and configure query engines for response generation over your content.

How do I ingest data from different sources for retrieval-augmented generation?▼

Ingest data for retrieval-augmented generation using 300+ connectors to load documents from local folders, web pages, GitHub, databases, and third-party sources into your index.

Can I use multimodal querying with my document index?▼

Yes, multimodal querying is supported. The framework provides multi-modal RAG patterns to query and generate responses across both text and image content within your indexes.

How do I persist a vector index to avoid re-indexing documents?▼

Persist a vector index to disk storage to avoid re-indexing. You can optionally save and load index storage for repeatable runs across your retrieval-augmented generation workflows.

What is the best way to create agent-based RAG workflows?▼

Create agent-based RAG workflows by configuring RAG agents that decide when to search your indexes and when to use tools, combining retrievers for chunk selection with query engines.

Does LlamaIndex support evaluating response quality in RAG applications?▼

Yes, evaluating response quality is supported. The framework includes evaluation hooks to measure RAG response quality, specifically assessing metrics like relevance and faithfulness.

Related Skills

Explore More Software Engineering Skills→
ihatesea69ihatesea69
3

llamaindex

Creates document ingestion, indexing and RAG pipelines for LLM applications with LlamaIndex.

Community
Advanced
agilebydesignagilebydesign
1

query-pinecone

Query the abd-answers Pinecone vector index for grounding chunks with similarity scores.

Official
Advanced
DevMHOneDevMHOne

omni-cache

Manage LLM response cache statistics, TTL policies, and semantic-similarity thresholds via API.

Community
Intermediate
ricablericable
1

@ruvector/agentic-integration

Coordinate distributed AI agents with shared vector memory and task routing.

Community
Advanced