> This page is for version 9.2 (default).
> For other versions, use one of these documentation indexes:
> - 9.2 (default): https://docs.nvidia.com/deepstream/9.2/llms.txt
> - Archives: https://docs.nvidia.com/deepstream/archives/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/deepstream/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/deepstream/_mcp/server.

# Service Maker for Python Developers

DeepStream Service Maker offers a Python package tailored for Python developers, providing essential bindings for Pipeline APIs alongside the high-level Flow APIs. Flow APIs are designed for beginners to quickly create common media processing and AI inference applications without requiring DeepStream knowledge, while Pipeline APIs enable advanced developers to further customize their applications.

## Python Service Maker Installation

To use DeepStream Service Maker Python APIs, you need to have the DeepStream SDK installed on your host ([DS Installation Guide](/text/DS_Installation)) or use it inside a DeepStream SDK Docker container ([DS Docker Container](/text/DS_docker_containers)). The Service Maker Python package is pre-installed globally in `/usr/local/lib/python3.12/dist-packages/pyservicemaker`.

#### [Quick Start Guide](/text/DS_service_maker_python_quick_start)

Install the Python package and run a first Service Maker application.

#### [Introduction to Flow APIs](/text/DS_service_maker_python_intro_to_flow_api)

High-level APIs for capture, inference, tracking, encoding, and output.

#### [Introduction to Pipeline APIs](/text/DS_service_maker_python_intro_to_pipeline_api)

Build and customize DeepStream pipelines with Python Pipeline APIs.

#### [Advanced Features](/text/DS_service_maker_python_advanced_features)

Probes, buffers, pipeline messages, OSD, and smart recording.

#### [Migration guide](/text/DS_service_maker_traditional_app_migration)

Move traditional DeepStream applications to Python Service Maker.