# Generate Inference

## How to generate Inferences?

<figure><img src="/files/25ujHZIsy7Ow0CIbNu5m" 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.


---

# Agent Instructions: 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:

```
GET https://docs.raga.ai/ragaai-prism/event-detection/generate-inference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.