> 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/upload-model.md).

# Upload Model

Upload event detection models into Prism. Start evaluations and monitor real-world performance.

## Steps to Upload a Model

* **Navigate to the Events Section**\
  Inside a specific run, go to the **Events** section.
* **Click on "Event Upload"**\
  Select the **"Event Upload"** button.
* **Specify Event Details**\
  Fill in the following details for the event:

  * **Event Name**
  * **Event Version**
  * **Event Types**
  * **Description**
  * Upload the **model/event zip file**

  **Note:** The zip file should have the same name as the model. Events are specific to the uploaded model.

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2F8OucbHNGICa58PhXYq5a%2FScreenshot%202024-09-23%20at%203.35.28%E2%80%AFPM.png?alt=media&amp;token=8fc205e1-6a9e-4a73-b98f-6e67e73fdd8f" alt=""><figcaption><p>Event Upload</p></figcaption></figure>

***

## Model Zip File Structure:

* The zip file should contain a folder with the **same name as the model**.
* Inside the folder, there must be a **`run.sh` script**.
* The `run.sh` script will be invoked with two arguments:\
  `<video_path>` and `<config.txt>`.
* `config.txt`  will have the list of config parameters which will be passed after video path .\[optional parameter]
* The tags in the `config.txt` have to be passed as a positional argument in `run.sh`
* The **`LD_LIBRARY_PATH`** (the folder containing the OpenCV library) will be provided by the user's engineering team and should be exported in the `run.sh` script. \[This is not required during event upload using UI]
* During runtime the current working directory will be the folder with model name.