skills.rest
Clay-HHK
Clay-HHKCOMMUNITY
Explore all skills by this author →
GitHub

llamaindex

Build retrieval-augmented question answering over private documents with vector indices.

2|Updated Apr 12, 2026
Search Tags:#rag#multimodal#agents#vector-index#llamaindex#document-qa#data-connectors
One-click install
npx skills add https://github.com/Clay-HHK/claude-config --skill llamaindex-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/Clay-HHK/claude-config/tree/main/skills/AI-research-SKILLs/14-agents/llamaindex
Command: npx skills add https://github.com/Clay-HHK/claude-config --skill llamaindex-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

LlamaIndex connects large language models to private and multi-source data so you can ask questions and build retrieval-augmented applications without manual document engineering. It removes the friction of ingesting, indexing, and querying heterogeneous documents so teams can build knowledge-driven features quickly.

Core Features & Use Cases

  • Document ingestion: 300+ connectors and readers to load files from local directories, web pages, GitHub, databases, and cloud storage.
  • Indexing & vector search: Create vector, list, and tree indices with persistent storage and multiple vector store integrations (Chroma, Pinecone, FAISS).
  • Query engines & agents: Configurable query engines, chat engines, and agents that combine document retrieval with tool use for RAG workflows.
  • Multimodal support & customization: Handle images and text, custom LLMs and embeddings, structured output via parsers, and metadata filtering for precise retrieval.
  • Use Case: Build a document Q&A chatbot that ingests enterprise docs, persists an index, and answers user queries with source citations.

Quick Start

Create a persistent vector index from your ./data directory and query it for "What is the main topic?".

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 application for private documents?▼

To build a RAG application, ingest unstructured private documents using data connectors, create vector indices for persistent storage, and configure query engines to retrieve and answer questions with source citations.

Can I load files from databases and cloud storage into a vector index?▼

Yes, you can load files from databases, local directories, web pages, and cloud storage using 300+ readers and connectors, then index them into vector stores like Chroma, Pinecone, or FAISS for retrieval.

Does LlamaIndex work with OpenAI and Anthropic LLMs for document Q&A?▼

Yes, LlamaIndex is compatible with OpenAI and Anthropic LLMs, allowing you to integrate custom models and embeddings for document Q&A, chatbots, and agent tool integration workflows.

What is the best way to handle multimodal inputs in a knowledge retrieval system?▼

To handle multimodal inputs, use indexing capabilities that process both images and text, apply metadata filtering for precise retrieval, and use structured output parsers to return formatted query results.

How do I query an enterprise knowledge base and return answers with source citations?▼

Query an enterprise knowledge base by creating a persistent vector index from ingested documents, then use configurable chat engines to retrieve accurate answers with source citations.

When should I use tree indices instead of vector indices for document search?▼

Use tree indices for hierarchical document summarization and list indices for sequential retrieval, while vector indices are optimal for semantic similarity search across unstructured private files.

Related Skills

Explore More Software Engineering Skills→
michaelalbermichaelalber
2

rag-pipeline-python

Scaffold end-to-end RAG pipelines for local or cloud LLMs.

Community
Advanced
svssdevasvssdeva
1

rag-implementation

Build Retrieval-Augmented Generation systems with semantic search and vector storage.

Community
Advanced
JhonHanderJhonHander

langchain-rag

Construct RAG pipelines with OpenAI embeddings and FAISS, Chroma, or Pinecone vector stores.

Community
Advanced
fgarofalo56fgarofalo56
6

langchain

Build LLM applications with chains, agents, memory, and RAG.

Community
Advanced