Pandas is required for the TAPAS tokenizer

[abdullawagih1]

I get this error when I used table-question-answering "google/tapas-base-finetuned-wtq".
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
"code": 400,
"type": "InternalServerException",
"message": "Pandas is required for the TAPAS tokenizer."
}

This error appears when I enter the data into the predictor endpoint as a table like this:
predictor.predict({
"inputs": {
"query": "How many stars does the transformers repository have?",
"table": {
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language": [
"Python",
"Python",
"Rust, Python and NodeJS"
]
}
},
})

So, how can I solve this issue?!