roboflow/roboflow-python

The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow has everything you need to build a computer vision application.

What it solves

This package provides a programmatic way to manage the entire computer vision lifecycle. It eliminates the need to manually upload data, manage versions, and trigger training or inference through a web interface, allowing developers to automate these workflows within Python scripts.

How it works

The library uses a hierarchical structure (Workspace $\rightarrow$ Project $\rightarrow$ Version) that mirrors the Roboflow platform. Users authenticate via API keys or a login command, then use Python objects to interact with their hosted assets. It supports uploading datasets in various formats (like YOLOv8 and Pascal VOC), deploying model weights, and running predictions on images via hosted or self-hosted inference servers.

Who it’s for

Computer vision engineers and data scientists who use the Roboflow platform to build, train, and deploy vision models.

Highlights

  • Full Lifecycle Management: Create projects, upload images/annotations, and start training directly from code.
  • Flexible Inference: Run predictions using hosted Roboflow models or self-hosted instances via Roboflow Inference.
  • Dataset Export: Search for specific images across a workspace and export them in multiple formats (e.g., COCO, YOLOv8).
  • Lightweight Option: Offers a roboflow-slim installation for embedded devices or CI pipelines that removes heavy dependencies like OpenCV and NumPy.

Related

  • Project
    roboflow/inference

    An inference engine and deployment platform that enables users to run computer vision models and complex visual workflows on any hardware, from edge devices to the cloud.

  • Project
    nndeploy/nndeploy

    A high-performance AI deployment framework that uses visual workflows to deploy AI models across desktop, mobile, and edge devices.

  • Project
    fmind/mlops-python-package

    A Python codebase implementing MLOps best practices and a professional toolchain to support the development of model registries, experiment tracking, and inference platforms.

  • Project
    roboflow/supervision

    A computer vision toolkit that provides model-agnostic building blocks for data loading, visualization, and dataset management to accelerate the development of vision applications.

  • Project
    langflow-ai/langflow

    Langflow is a visual platform for building and deploying AI agents and workflows, allowing developers to design, test, and export AI logic as APIs or MCP servers.