skills.rest
box755
box755COMMUNITY
Explore all skills by this author →
GitHub

llamaindex

Builds document-grounded Q&A and RAG pipelines with LlamaIndex ingestion, indexing, and querying.

Updated Aug 23, 2026
Search Tags:#rag#multimodal#document ingestion#llamaindex#agent tools#query engine#vector indexing
One-click install
npx skills add https://github.com/box755/simlens-research --skill llamaindex-box755
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/box755/simlens-research/tree/main/skill-packs/AI-Research-SKILLs/14-agents/llamaindex
Command: npx skills add https://github.com/box755/simlens-research --skill llamaindex-box755

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

LlamaIndex helps you turn private and heterogeneous documents into a retrieval-augmented question-answering system, so you can ask accurate questions and produce grounded answers without manual indexing or glue code.

Core Features & Use Cases

  • Document ingestion (300+ connectors): Load files, web pages, GitHub repos, and many enterprise sources, then normalize them into a unified document format.
  • Indexing and retrieval: Create vector (and other) indices, persist them to storage, and retrieve relevant chunks with similarity search and metadata filtering.
  • Query engines and agents: Support chat and query patterns (including streaming), wrap query engines as tools, and enable RAG-capable agents for multi-step workflows.
  • Multimodal and structured outputs: Handle image+text inputs for multimodal RAG and produce structured responses using Pydantic output parsers.

Quick Start

Ask an AI: Build a 5-line RAG pipeline using LlamaIndex to load documents from a local folder, create a vector index, and query it with a question.

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 over my local documents?▼

To build a RAG pipeline, ingest heterogeneous data using 300+ connectors to normalize files into a unified format, create vector indices, and execute query engines to generate grounded answers from retrieved context.

How does document ingestion work for enterprise data sources?▼

Document ingestion normalizes files, web pages, and enterprise sources into a unified document format using over 300 connectors, enabling seamless vector indexing and retrieval without manual glue code.

Can I use metadata filtering for vector indexing retrieval?▼

Yes, vector indexing supports metadata filtering. You can persist indices to storage and retrieve relevant chunks using similarity search combined with configurable metadata filters for precise context retrieval.

Does LlamaIndex support multimodal RAG and structured outputs?▼

Yes, multimodal RAG handles image and text inputs for comprehensive document processing. Structured responses are generated using Pydantic output parsers to enforce specific response schemas.

What is the best way to enable agent tools for multi-step query workflows?▼

The best way to enable multi-step workflows is wrapping query engines as tools. This creates RAG-capable agents that execute streaming queries and perform complex reasoning over retrieved document context.

Do I need Pydantic to parse structured responses from query engines?▼

Yes, Pydantic is required for structured output parsing. Query engines use Pydantic output parsers alongside LLM-driven response generation to produce configurable, structured answers from retrieved context.

Related Skills

Explore More Software Engineering Skills→
jonnabiojonnabio
6

llamaindex

Build RAG applications with document ingestion, indexing, and querying.

Community
Advanced
mgd34msumgd34msu
6

ai-integration

Integrate AI and LLM features like chat, streaming, RAG, and function calling.

Community
Advanced
jonnabiojonnabio
6

instructor

Extract structured data from LLM responses with Pydantic validation.

Community
Advanced
eyadsibaieyadsibai
7

rag-frameworks

Compare RAG frameworks like LangChain and LlamaIndex for document QA.

Community
Intermediate