Skip to main content

Getting Started

Overview​

LlamaExtract provides a simple API for extracting structured data from unstructured documents like PDFs and text files (with image support coming soon).

LlamaExtract is available as a web UI, Python SDK and (coming soon) REST API. It is currently a experimental feature; you can sign up to try it out or read the onboarding documentation

Quick Start​

Using the web UI​

The simplest way to try out LlamaExtract is to use the web UI.

Just define your Extraction Agent (schema and settings), drag and drop any supported document into LlamaCloud and extract data from your documents.

Extraction Results

Get an API key​

Once you're ready to start coding, get an API key to use LlamaExtract with the Python SDK.

Use our libraries​

We have a library available for Python. Check out the Python quick start to get started.

REST API (Coming Soon!)​

The REST API, while available, is not stable for public use. If you're using a different language, please reach out to us on Discord and let us know so that we can prioritize this.