[go: nahoru, domu]
Skip to main content

Getting Started

Overview​

Welcome to LlamaParse, the world's best document parsing service, from LlamaIndex. LlamaParse is a component of LlamaCloud that allows you to parse complex documents such as PDFs, PowerPoints, Word documents and spreadsheets into structured data. It's available as a standalone REST API, a Python package, a TypeScript SDK, and a web UI. It is currently in a public beta; you can sign up to try it out or read the onboarding documentation.

Why LlamaParse?​

At LlamaIndex we have a mission to connect your data to LLMs. A key factor in the effectiveness of presenting your data to LLMs is that it be easily understood by the model. Our experiments show that high-quality parsing makes a significant difference to the outcomes of your generative AI applications. So we compiled all of our expertise in document parsing into LlamaParse, to make it easy for you to get your data into the best possible shape for your LLMs.

Quick starts​

Using the web UI​

The fastest way to try out LlamaParse is to use the web UI. Just drag and drop any PDF, PowerPoint, Word document, or spreadsheet into LlamaCloud and see your results in real time. This is great for getting a sense of what LlamaParse can do before you integrate it into your code.

Get an API key​

Once you're ready to start coding, get an API key to use LlamaParse in Python, TypeScript or as a standalone REST API.

Use our libraries​

We have libraries available for Python and TypeScript. Check out the Python quick start or the TypeScript quick start to get started.

Use the REST API​

If you're using a different language, you can use the LlamaParse REST API to parse your documents.