# Test Endpoints

Test your deployment endpoints directly from the Valohai web app to verify they're working before integrating with production systems.

### Test from the UI

1. Open your project
2. Navigate to the **Deployment** tab
3. Select your deployment
4. Click **Test deployment**
5. Choose your endpoint from the drop-down
6. Provide the required input fields
7. Click **Send request**

The response from your inference service appears directly in your browser.

### Input types

Depending on what your endpoint expects, you can send:

**Text/JSON data:** Type directly into form fields

**Files:** Upload images, documents, or other binary data

**Multiple fields:** Add multiple inputs if your endpoint accepts several parameters

### Example workflow

For an image classification endpoint:

1. Select the `predict-digit` endpoint
2. Add a field named `image`
3. Change the type to **File**
4. Upload a test image
5. Send the request
6. Review the prediction response

***

**Production testing:** For programmatic testing, use curl or your preferred HTTP client:

```shell
curl -X POST https://valohai.cloud/your-org/your-project/deployment/production/predict \
  -F "image=@test_image.png"
```

**Next:** Learn how to [monitor endpoint performance](https://github.com/valohai/dokuhai/blob/main/docs/monitor.md) in production.


---

# 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.valohai.com/serving-your-models/real-time-endpoints/test-endpoints.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.