# Getting Started Once you create an account, the first step is to start a project: 1. Choose a name for the project 2. Choose a project type (supports span-based, character-based annotation, OCR Annotation and Image Classification) 3. Choose the primary document language: This step is important as it determines the tokenization to produce the annotation 4. Write a detailed description for your project with guideline specifications for each entity 5. Input your entity types: You can either add entities manually by adding name, color and shortcut for each entity or you can upload a CSV file by clicking on "+ Add new label set" containing three seperate columns: entity name, shortcut and the color code. 6. Input your relation types: You can either add relations manually by adding name and shortcut for each relation or upload a CSV file by clicking on "+ Add new label set" containing relation names and associated shortcuts. 7. Input your class types: You can choose binary (positive/negative), single class or multi-class for text classification 8. Save your project {% embed url="" %} --- # 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://ubiai.gitbook.io/ubiai-documentation/getting-started.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.