skills.rest
EanLee
EanLeeCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

llamaindex

Build LLM applications with data ingestion, indexing, and RAG querying.

Updated Dec 16, 2025
Search Tags:#indexing#llm#rag#agents#data ingestion#llamaindex#querying
One-click install
npx skills add https://github.com/EanLee/article-write --skill llamaindex-eanlee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/EanLee/article-write/tree/main/.github/skills/llamaindex
Command: npx skills add https://github.com/EanLee/article-write --skill llamaindex-eanlee

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires llama-index, openai, anthropic, and includes references (resource) components.

What problem does it solve?

This Skill enables developers to build powerful Large Language Model (LLM) applications by seamlessly connecting them to diverse data sources, facilitating advanced data ingestion, indexing, and querying capabilities.

Core Features & Use Cases

  • Data Ingestion: Connects to over 300 data sources (files, web pages, databases, APIs) for comprehensive data loading.
  • Indexing & Querying: Creates various indices (vector, list, tree) for efficient data retrieval and supports sophisticated query engines for asking questions.
  • RAG Pipelines: Specializes in building Retrieval-Augmented Generation (RAG) systems for question-answering over private data.
  • Agents: Allows the creation of intelligent agents that can use tools, including document retrieval, for complex task execution.
  • Use Case: Build a chatbot that can answer questions about your company's internal documentation by ingesting all relevant documents and using LlamaIndex to retrieve and synthesize answers.

Quick Start

Use the llamaindex skill to load documents from the 'data' directory and create a vector index for querying.

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 pipeline for querying private documents?▼

To build a RAG pipeline, ingest documents from data sources like files or APIs, create vector indices for efficient retrieval, and use query engines to synthesize answers from private data.

Can I connect an LLM application to my internal company documentation?▼

Yes, you can connect an LLM to internal company documentation by using over 300 data connectors to ingest files, web pages, databases, and APIs, enabling a chatbot to answer questions over your private data.

What data sources can I use for data ingestion with LlamaIndex?▼

Data ingestion supports over 300 data sources, including files, web pages, databases, and APIs, allowing comprehensive data loading to connect LLMs to diverse private data for retrieval.

Does LlamaIndex support intelligent agents for complex task execution?▼

Yes, it allows the creation of intelligent agents that can use tools, including document retrieval, to execute complex tasks and augment LLM applications with agentic capabilities.

What index types are available for efficient knowledge retrieval?▼

Available index types include vector indices, list indices, and tree indices, which enable efficient data retrieval and support sophisticated query engines for asking questions over ingested data.

Related Skills

Explore More Software Engineering Skills→
Clay-HHKClay-HHK
2

llamaindex

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

Community
Advanced
ricablericable

llamaindex

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

Community
Advanced
hhhi21ghhhi21g

llamaindex

Create RAG applications with document indexing and querying via LlamaIndex.

Community
Advanced
tadod12tadod12

llamaindex

Automate data-centric LLM application building with LlamaIndex pipelines.

Community
Advanced