"I have textual data and I want to build a model that understands all the information, so that when I ask any question, it can reply accordingly."
predictor = model1.deploy(initial_instance_count=1, instance_type="ml.p3.2xlarge")
import json
Prepare the question you want to ask
question = "What is the age of the patient?"
Convert the question to JSON format (if needed by your model)
question_input = json.dumps({"question": question})
Perform inference using the deployed predictor
answer_result = predictor.predict(question_input)
Parse and display the answer
parsed_answer = json.loads(answer_result)
answer = parsed_answer["answer"]
print("Answer:", answer)
----This is Errors---
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received server error (0) from primary with message "Your invocation timed out while waiting for a response from container primary. Review the latency metrics for each container in Amazon CloudWatch, resolve the issue, and try again.". See https://us-east-1.console.aws.amazon.com/cloudwatch/home?region=us-east-1#logEventViewer:group=/aws/sagemaker/Endpoints/pytorch-inference-2023-08-10-12-34-42-075 in account 962041679118 for more information.