Trigger the loop when a network request is made with a JSON body containing an array of strings to cluster and the desired number of clusters.

Create a K-means clustering algorithm and then use it to cluster the embeddings from the BLOCK_INPUT. The clustering should be done locally without calling external APIs, including OpenAI. Only use OpenAI for getting the embeddings -- use the `text-embedding-3-small` model. Please write code for a k-means clustering algorithm, don't use a pre-built library, and ensure the embeddings are generated by calling the OpenAI API. 

Return the original strings clustered based on the simulated or locally generated embeddings.

Replace the simulated embeddings with calls to OpenAI for the `text-embedding-3-small` model. Sample code looks like:
```curl
curl https://api.openai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "input": "Your text string goes here",
    "model": "text-embedding-3-small"
  }'
```

And the response should look like:
```json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.006929283495992422,
        -0.005336422007530928,
        ... (omitted for spacing)
        -4.547132266452536e-05,
        -0.024047505110502243
      ],
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}
```

Return the clustered strings as a JSON response.

Cluster strings using OpenAI embeddings and clustering techniques

magic loops

ClusterStrings