llamaindex

Build and deploy LLM applications over custom data with LlamaIndex.

40|6|Updated Jul 11, 2026

Search Tags:#knowledge graph #llm #rag #agents #observability #llamaindex

Ready to run

npx skills add https://github.com/magnus919/agent-skills --skill llamaindex-magnus919

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/magnus919/agent-skills/tree/main/llamaindex
Command: npx skills add https://github.com/magnus919/agent-skills --skill llamaindex-magnus919

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires llama-index, llama-index-core, llama-index-llms-openai, llama-index-vector-stores-qdrant, llama-index-embeddings-openai, llama-parse, llama-deploy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill addresses the complexity of building LLM applications over private data, providing a structured framework to move from raw documents to production-ready RAG pipelines and event-driven agent systems.

Core Features & Use Cases

Production RAG Pipelines: Orchestrate data ingestion, hybrid retrieval, and reranking to ensure high-quality, grounded answers.
Agentic Workflows: Design multi-agent systems using event-driven primitives for complex, multi-step reasoning tasks.
Knowledge Graph Construction: Build structural path traversals using PropertyGraphIndex to augment vector-based retrieval.

Quick Start

Load the llamaindex skill and run the check-setup script to verify your environment and dependencies are correctly configured for your RAG pipeline.

Frequently Asked Questions about llamaindex

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

FAQPage Schema

How do I build production-grade RAG pipelines over custom data?▼

Build production-grade RAG pipelines by orchestrating data ingestion, hybrid retrieval, and reranking over custom data. This framework structures the process from raw documents to grounded answers using event-driven workflows and retrieval-augmented generation.

How do I orchestrate multi-agent systems for complex reasoning tasks?▼

Orchestrate multi-agent systems by designing workflows with event-driven primitives. This approach enables complex, multi-step reasoning tasks by coordinating multiple agents through structured event-driven workflows.

Can I use Qdrant as a vector store with LlamaIndex for RAG pipelines?▼

Yes, Qdrant is supported as a vector store for RAG pipelines. The environment integrates llama-index-vector-stores-qdrant alongside OpenAI embeddings to manage vector-based retrieval and storage.

What Python version is required to deploy LlamaIndex applications?▼

Python 3.8 or higher is required to deploy LlamaIndex applications. Running the check-setup script verifies your environment and dependencies are correctly configured for your RAG pipeline.

Does this framework support production observability for LLM workflows?▼

Yes, production observability is supported for LLM workflows. The framework provides structured tools to monitor event-driven workflows and retrieval-augmented generation in production environments.