llamaindex

Build retrieval-augmented question answering over private documents with LlamaIndex.

Updated Feb 15, 2026

Search Tags:#knowledge retrieval #rag #agents #document ingestion #vector index #llamaindex #query engine

Ready to run

npx skills add https://github.com/ricable/mcai --skill llamaindex-ricable

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/ricable/mcai/tree/main/.agents/skills/llamaindex
Command: npx skills add https://github.com/ricable/mcai --skill llamaindex-ricable

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you turn scattered documents, web pages, databases, and APIs into searchable knowledge for LLM applications, eliminating the complexity of building retrieval pipelines by hand.

Core Features & Use Cases

Document ingestion: Load content from files, web pages, GitHub repos, PDFs, and APIs.
Indexing and retrieval: Build vector, list, or tree indices and query them with flexible response modes.
Agents with tools: Combine retrieval with function tools for multi-step reasoning and task automation.
Use cases: Knowledge bases, document Q&A, internal chatbots, multimodal search, and enterprise RAG workflows.

Quick Start

Use the llamaindex skill to ingest your documents, build an index, and answer questions from a local data folder.

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 over private documents?▼

To build a RAG application, you ingest documents from files or APIs, build a vector index, and use a query engine for retrieval-augmented question answering over your private data.

What is the best way to ingest files for a document Q&A workflow?▼

For a document Q&A workflow, you can ingest content directly from local files, PDFs, web pages, GitHub repos, and APIs to build a searchable knowledge base for your LLM applications.

Can I use agents with tools for multi-step reasoning in enterprise search?▼

Yes, you can combine retrieval with function tools to build agents for multi-step reasoning and task automation within your enterprise search and knowledge base workflows.

Does this approach support multimodal retrieval for knowledge bases?▼

Multimodal retrieval is supported, allowing you to extract and query searchable knowledge from diverse data formats alongside standard text indexing for comprehensive document Q&A.

Do I need vector indices to query internal chatbots?▼

Vector indices are required for querying internal chatbots, though you can also build list or tree indices to enable flexible response modes and metadata filtering during knowledge retrieval.