> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/changelog/explore-by-month/august-2025/run-custom-python-on-workflows.md).

# Run Custom Python on Workflows

<figure><img src="/files/iekDxbHDlQe50amybeEU" alt=""><figcaption></figcaption></figure>

You can now use custom Python blocks within Roboflow Workflows via the [serverless v2 API](/deploy/serverless-hosted-api-v2.md). Previously, only supported on [Dedicated Deployments](/deploy/dedicated-deployments.md) or via local inference, you can now unlock the full power of custom code and add your own logic, intricate visualizations, and much more.

Learn more about how the Custom Python block execution works in [our inference docs](https://inference.roboflow.com/workflows/custom_python_code_blocks/), as well as see the [packages that are supported](https://github.com/roboflow/inference/blob/main/requirements/_requirements.txt) when running those blocks.&#x20;

{% hint style="info" %}
Custom Python is now supported on Serverless V2, Dedicated Deployments, as well as when running `inference` locally.
{% endhint %}

You can also now have an [AI assistant write code](/changelog/explore-by-month/august-2025/use-an-ai-assistant-with-custom-python-blocks.md) within your Custom Python blocks as well.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.roboflow.com/changelog/explore-by-month/august-2025/run-custom-python-on-workflows.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.