# Process documents Once your project is configured, you can start uploading data to Metamaze. In the beginning, you will not have any trained models, unless you added an existing document type to your project, in which case you will already have a trained entity extraction model for that document type. Trained models are needed in order to automatically process uploaded files. In order to train your models, you need annotated data. This chapter covers how to upload data to Metamaze and how to get started with labelling. * **Uploading data** - How to upload files into the system for annotation. * **Uploads overview** - Explanation of what you see on the uploads overview page. * **Document** **view** - Explanation of what you see on the document overview page. * **Annotation of training data** - How to annotate a document. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs-old.app.metamaze.eu/getting-started/processing-documents.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.