Skip to main content

python client for the Roboflow application

Project description

Roboflow Python

roboflow logo

Roboflow streamlines your computer vision pipeline - upload data, label it, download datasets, train models, deploy models, and repeat.

The Roboflow Python Package is a python wrapper around the core Roboflow web application and REST API.

We also maintain an open source set of CV utililities and notebook tutorials in Python:


To install this package, please use Python 3.6 or higher.

Install from PyPi (Recommended):

pip install roboflow

Install from Source:

git clone
cd roboflow-python
python3 -m venv env
source env/bin/activate
pip3 install -r requirements.txt


import roboflow



Download any of over 200,000 public computer vision datasets from Roboflow Universe. Label and download your own datasets on

import roboflow
dataset = roboflow.download_dataset(dataset_url="", model_format="yolov8")
#ex. dataset = roboflow.download_dataset(dataset_url="", model_format="yolov8")


Predict with any of over 50,000 public computer vision models. Train your own computer vision models on or train upload your model from open source models - see

img_url = ""
universe_model_url = ""

model = roboflow.load_model(model_url=universe_model_url)
pred = model.predict(img_url, hosted=True)

Library Structure

The Roboflow python library is structured by the core Roboflow application objects.

Workspace ( --> Project ( --> Version (

from roboflow import Roboflow
rf = Roboflow()
workspace = rf.workspace("WORKSPACE_URL")
project = workspace.project("PROJECT_URL")
version = project.version("VERSION_NUMBER")

The workspace, project, and version parameters are the same that you will find in the URL addresses at and

Within the workspace object you can perform actions like making a new project, listing your projects, or performing active learning where you are using predictions from one project's model to upload images to a new project.

Within the project object, you can retrieve metadata about the project, list versions, generate a new dataset version with preprocessing and augmentation settings, train a model in your project, and upload images and annotations to your project.

Within the version object, you can download the dataset version in any model format, train the version on Roboflow, and deploy your own external model to Roboflow.


If you want to extend our Python library or if you find a bug, please open a PR!

Also be sure to test your code the unittest command at the /root level directory.

Run tests:

python -m unittest

When creating new functions, please follow the Google style Python docstrings. See example below:

def example_function(param1: int, param2: str) -> bool:
    """Example function that does something.

        param1: The first parameter.
        param2: The second parameter.

        The return value. True for success, False otherwise.


We provide a Makefile to format and ensure code quality. Be sure to run them before creating a PR.

# format code with `black` and `isort`
make style

# check code with flake8
make check_code_quality

Note These tests will be run automatically when you commit thanks to git hooks.

Project details

Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

roboflow-1.1.1.tar.gz (49.2 kB view hashes)

Uploaded Source

Built Distribution

roboflow-1.1.1-py3-none-any.whl (57.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page