Skip to main content

Welcome to LlamaCloud 🦙

LlamaCloud is a hosted service for document processing and search, powered by LlamaIndex. It consists of three primary components:

Parse​

Parse transforms complex documents into LLM-ready structured data with:

  • Support for 50+ file formats (PDF, DOCX, PPTX, XLSX, HTML, EPUB, images)
  • Advanced parsing capabilities including tables, charts, and layout extraction
  • Multimodal parsing options using vendor models for complex documents
  • Customizable parsing with Fast, Balanced, Premium, and Custom modes

Extract​

Extract transforms complex documents into well-typed structured data with:

  • Customizable extraction agents and schemas
  • Batch processing capabilities for scale
  • Iterative schema development

Index​

Index transforms document collections into searchable knowledge bases with:

  • Seamless integration with popular vector databases
  • Automated syncing from data sources to vector stores
  • Built-in query interface for retrieving relevant information
  • Customizable indexing pipeline for RAG applications

Get started with Web UI, Python SDK, and REST API. Sign up for an account to get started or explore the documentation for each component.

OSZAR »