Agent skill · data analytics · davila7
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
Why this skill is useful
Adds a comprehensive framework for document ingestion, indexing, and querying that enables advanced RAG applications with LLMs, which the AI cannot generate on its own.
What it needs
Requires llama-index installed locally. Requires anthropic, openai account access. About 6k tokens when loaded. Last updated 2026-08-06. 30,138 stars on the source repository.
What this skill does
LlamaIndex - Data Framework for LLM Applications The leading framework for connecting LLMs with your data. When to use LlamaIndex Use LlamaIndex when: Building RAG (retrieval-augmented generation) applications Need document question-answering over private data Ingesting data from multiple sources (300+ connectors) Creating knowledge bases for LLMs Building chatbots with enterprise data Need structured data extraction from documents Metrics: 45,100+ GitHub stars 23,000+ repositories use LlamaIndex 300+ data connectors (LlamaHub) 1,715+ contributors v0.14.7 (stable) Use alternatives instead: LangChain: More general-purpose, better for agents Haystack: Production search pipelines txtai: Lightweight semantic search Chroma: Just need vector storage Quick start Installation 5-line RAG example Core concepts 1. Data connectors - Load documents 2. Indices - Structure data 3. Query engines - Ask questions 4. Retrievers - Find relevant chunks Agents with tools Basic agent RAG agent (document search + tools) Advanced RAG patterns Chat engine (conversational) Metadata filtering Structured output Data ingestion patterns Multiple file types Web scraping Database API endpoints Vector store integrations Chroma (local) Pinecone (cloud) FAISS (fast) Customization Custom LLM Custom embeddings Custom prompt templates Multi-modal RAG Image + text Evaluation Response quality Best practices 1. Use vector indices for most cases - Best performance 2. Save indices to disk - Avoid re-indexing 3. Chunk documents properly - 512-1024 tokens optimal 4. Add metadata - Enables filtering and tracking 5. Use streaming - Better UX for long responses 6. Enable verbose during dev - See retrieval process 7. Evaluate responses - Check relevance and faithfulness 8. Use chat engine for conversations - Built-in memory 9. Persist storage - Don't lose your index 10. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills davila7/agents-llamaindex