LlamaIndex
Definición
LlamaIndex focuses on connecting LLMs to your data: ingestion, indexing, and querying. It provides flexible RAG pipelines, multiple index types, and evaluation tools.
Complementa LangChain: LlamaIndex emphasizes the data layer (documents, embeddings, vector stores, indexing strategies). Úselo cuando your priority is robust RAG over your own docs, APIs, or databases, with control over chunking, recuperación, and synthesis. Also supports agents and query engines.
Cómo funciona
Cargar datos desde documentos, APIs o bases de datos en un formato de documento unificado. Construir índices: índice vectorial (embeddings + vector store), keyword index, or hybrid; you choose node parsers (chunking), embedding model, and index type. Query engines run recuperación (optionally with reranking) and then synthesis (the LLM answers from retrieved nodes). You can customize retrievers, node parsers, and response synthesis (por ej. tree summarization, simple concatenation). Evaluation tools (por ej. faithfulness, relevance) help tune chunking and recuperación for production RAG. Agents can use LlamaIndex query engines as tools inside LangChain or native agent loops.
Casos de uso
LlamaIndex fits when you need flexible RAG indexing, query engines, and evaluation over your own data and APIs.
- RAG and document Q&A with flexible indexing and query engines
- Connecting LLMs to internal data (docs, APIs, databases)
- Evaluating and tuning recuperación and synthesis for production RAG