Amazon SageMaker

Input

Supported content types: text/plain As such there is no character limit on the query. The query should be coherent and focused on a single topic. The system may have problem in capturing context across multiple sentences so it is advised to stick to a single sentence query

Sample Input queries :

1. Create confusion matrix ?
2. How to input a csv file in Java ?
3. Convert a date string into yyyymmdd format

Output

Content type: text/csv Sample Output: | Result | Function Name | URL
|----------|------------------- |------------------------------------------------------- | Result 1| Create | https://github.com/cloudfoundry/sample.java/....

Invoking endpoint

AWS CLI Command

If you are using real time inferencing, please create the endpoint first and then use the following command to invoke it:

!aws sagemaker-runtime invoke-endpoint --endpoint-name $model_name --body fileb://$input.json--content-type 'text/plain' --region us-east-2 output.csv

Substitute the following parameters:

• "endpoint-name" - name of the inference endpoint where the model is deployed
• input.json - input json with query
• application/json - MIME type of the given input
• out.json - filename where the inference results are written to.

Resources

Link to Instructions Notebook: https://tinyurl.com/str99ss Link to Sample Input: https://tinyurl.com/utsqgbz Link to Sample Output: https://tinyurl.com/rznuxsw

Mphasis Autocode.AI
Sample Input File
Sample Jupyter Notebook