llamaindex

Build RAG pipelines with document ingestion, vector indexing, and query engines.

13.0k|930|Updated Nov 3, 2025

Search Tags:#llm #rag #chatbot #document ingestion #vector index #llamaindex #query engine

Ready to run

npx skills add https://github.com/Orchestra-Research/AI-research-SKILLs --skill llamaindex-orchestra-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/Orchestra-Research/AI-research-SKILLs/tree/main/14-agents/llamaindex
Command: npx skills add https://github.com/Orchestra-Research/AI-research-SKILLs --skill llamaindex-orchestra-research

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Connecting LLMs to private data requires building document ingestion, indexing, and retrieval infrastructure from scratch, which is time-consuming and error-prone. ## Core Features & Use Cases - Document Ingestion: Load data from 300+ connectors including files, web pages, GitHub, databases, and APIs. - Indexing & Querying: Create vector, list, and tree indices with configurable query engines supporting streaming, metadata filtering, and structured output. - Agents & Chat: Build function-calling agents and conversational chat engines with memory over your documents. - Use Case: Build a document Q&A chatbot over your company's internal documentation by loading files with SimpleDirectoryReader, creating a VectorStoreIndex, and querying it through a chat engine with conversation memory. ## Quick Start Ask the AI to build a RAG application that loads documents from a folder and answers questions about them using LlamaIndex.

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 with LlamaIndex?▼

Load documents with SimpleDirectoryReader, create a VectorStoreIndex from them, then call index.as_query_engine() to query. The whole pipeline takes about five lines of Python code.

LlamaIndex vs LangChain for document Q&A?▼

LlamaIndex specializes in RAG with 300+ data connectors and a simpler API for document Q&A. LangChain is more general-purpose and better suited for complex multi-step agent workflows.

Does LlamaIndex support vector databases like Pinecone?▼

Yes, LlamaIndex integrates with Chroma, Pinecone, FAISS, and other vector stores through StorageContext. Pass the vector store when creating the index to persist embeddings externally.

Can LlamaIndex chat engines remember conversation history?▼

Yes, use index.as_chat_engine() with chat_mode set to condense_plus_context for multi-turn conversations with built-in memory. Call chat_engine.reset() to clear history and start fresh.

When should I not use LlamaIndex?▼

Avoid LlamaIndex when building complex general-purpose agents, where LangChain fits better, or when you only need vector storage, where Chroma alone suffices. It is optimized for data-centric RAG applications.