> ## Documentation Index
> Fetch the complete documentation index at: https://docs.paradigm-shift.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Pulse

> Add a new datapoint to train a vision model based on reinforcement learning

This endpoint allows users to create a new feedback entity. This entity will then be used to train the model based on reinforcement learning.

<RequestExample>
  ```bash bash theme={null}
  # CURL request to train GRPO model with image support
  curl -X POST http://your-api-endpoint.com/your-route \
    -H "Content-Type: application/json" \
    -d '{
      "data": [
        {
          "question": "what is the brand of phone?",
          "answer": "nokia",
          "image": "/home/jovyan/shares/SR004.nfs2/data/textvqa/train_images/0054c91397f2fe05.jpg",
          "width": 512,
          "height": 365,
          "bboxs": [[168, 168, 193, 178]],
          "dataset": "textvqa",
          "split": "train"
        },
        {
          "question": "what type of plane is this?",
          "answer": "lape",
          "image": "/home/jovyan/shares/SR004.nfs2/data/textvqa/train_images/005635e119b9f32f.jpg",
          "width": 512,
          "height": 333,
          "bboxs": [[265, 154, 304, 167]],
          "dataset": "textvqa",
          "split": "train"
        }
      ]
    }'
  ```

  ```typescript nodejs theme={null}
  const formData = new FormData();
    formData.append("datasetname", "set1");

    // Add image files
    const fileInput = document.querySelector("#fileInput");
    for (const file of fileInput.files) {
      formData.append("files", file);
    }

    const response = await fetch(endpoint, {
      method: "POST",
      headers: {
        "x-api-key": apiKey,
  		"Content-Type": "application/json"
      },
      body: formData
    });
  ```
</RequestExample>

<ResponseField name="response" type="string">
  Enter a description
</ResponseField>