> For the complete documentation index, see [llms.txt](https://docs.raga.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raga.ai/ragaai-prism/event-detection/generate-inference.md).

# Generate Inference

Run inferences with event detection models. Evaluate predictions and test outputs instantly.

## How to generate Inferences?

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2Flexqucp1izPI1PGsDEwp%2FScreenshot%202024-09-23%20at%209.28.58%E2%80%AFAM.png?alt=media&amp;token=bc03fee7-28bb-4444-8321-be16171b19b8" alt=""><figcaption><p>Generate inferences</p></figcaption></figure>

1. **Navigate to the Run**\
   Inside a specific run, click on the **"Generate New Inferences"** button to begin.
2. **Select Dataset and Model**\
   Choose the **dataset** and the **model name** that you want to use for inference generation.
3. **Choose Model Version**\
   Select the **version** of the chosen model to run the inferences on.
4. **Optional: Apply Time Filters**\
   You can filter inferences by time to focus on a specific range of data. Use the time filter to narrow down the set of  data points.
5. **Optional: Apply Attribute Filters**\
   Add custom attribute filters by clicking on the **"+ Add Attributes"** button to refine the dataset further.
6. **Generate Inferences**\
   Once everything is set, click the **"Generate Inferences"** button to begin the process.