Multimodal Dataset

<dataset-name>/
├── images/
│   ├── <image-name>.jpg
│   └── <image-name>.jpg
│   ├── .....
│   └── <image-name>.jpg
└── <dataset-name>.jsonl

[
  {
    "question": "Which number should be written in place of the question mark? <image>",
    "answer": "60"
  },
  {
    "question": "Which bike is most expensive? Options:[ 'A', 'B', 'C', 'D', 'E' ] <image>",
    "answer": "A"
  },
  {
    "question": "Which kite has the longest string? Options:[ 'A', 'B', 'C', 'D', 'E' ] <image>",
    "answer": "C"
  }
]

{
	"conversations": [
		{
			"from": "system", 
			"value": "<system-prompt>"
		},
		{
			"from": "human",
	    "value": "<question>"
	  },
	  {
		  "from": "gpt",
		  "value": "<answer>"
		}
	],
	"image": "images/<image-name>.jpg"
}

{"conversations": [{"from": "system", "value": "You are a helpful assistant that answers questions based on the given image."}, {"from": "human", "value": "Which number should be written in place of the question mark?\n<image>"}, {"from": "gpt", "value": "60"}], "image": "images/1.jpg"}
{"conversations": [{"from": "system", "value": "You are a helpful assistant that answers questions based on the given image."}, {"from": "human", "value": "Which bike is most expensive?\n Options: A, B, C, D, E\n<image>"}, {"from": "gpt", "value": "A"}], "image": "images/2.jpg"}
{"conversations": [{"from": "system", "value": "You are a helpful assistant that answers questions based on the given image."}, {"from": "human", "value": "Which kite has the longest string?\n Options: A, B, C, D, E\n<image>"}, {"from": "gpt", "value": "C"}], "image": "images/3.jpg"}

mathvision/
├── images/
│   ├── 1.jpg
│   ├── 2.jpg
│   └── 3.jpg
└── mathvision.jsonl

import os
import asyncio
from impulse.api_sdk.sdk import ImpulseSDK
from impulse.api_sdk.models import (
    DatasetCreate,
)


async def main():
    async with ImpulseSDK(os.environ.get("IMPSDK_API_KEY")) as client:
        files = await client.dataset.list_datasets()
        await client.dataset.upload_dataset("<file-path>/<filename>.zip", DatasetCreate(name="<dataset name>", description="<dataset description>"))

        print(files)

asyncio.run(main())