# Create a Project

`Workspace.create_project()` creates a new project in the workspace and returns a `Project` object you can then upload images to.

```python
import roboflow

rf = roboflow.Roboflow(api_key="YOUR_API_KEY")

project = rf.workspace().create_project(
    project_name="Flower detector",
    project_type="object-detection",
    project_license="MIT",
    annotation="flowers",
)
print(project.id)
```

## Parameters

* `project_name` (str) - the display name. The URL slug is auto-generated from this.
* `project_type` (str) - one of:
  * `object-detection`
  * `classification`
  * `instance-segmentation`
  * `semantic-segmentation`
  * `keypoint-detection`
* `project_license` (str) - set to `"Private"` for private projects (paid plans only). Public-license values include `"MIT"`, `"CC BY 4.0"`, `"Public Domain"`, etc. - see the project creation form in the web app for the full list.
* `annotation` (str) - the annotation group: a noun describing what's being labeled (`"flowers"`, `"vehicles"`, `"defects"`). Used in the labeling UI prompts.

## REST and CLI equivalents

* REST: see [Create a Project (REST)](/developer/rest-api/create-a-project.md).
* CLI: see [Create a Project (CLI)](/developer/command-line-interface/create-a-project.md).


---

# 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.roboflow.com/developer/python-sdk/create-a-project.md?ask=<question>
```

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.