Amazon SageMaker

Input

1) The input file should be a zip of text files (.txt) in utf-8 encoding

2) The zipped file can have a maximum of 30 documents

3) The maximum size of the each file should be <= 10KB (1000 lines)

4) Supported Content type: application/zip

Output

1) The output from the model is a json file, supported content type: application/json

2) The processed output is a json file which has lists of documents clusters, each representing the documents grouped on the basis of similar information

3) Sample output file:

{

“Cluster –1” : [“Doc-1”, “Doc-6”, “Doc-3”, “Doc-7”, “Doc-8”],

“Cluster –2” : [“Doc-2”, “Doc-4”]

}

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 "endpoint-name" --body fileb://input.zip --content-type application/zip --accept application/json result.json 

Substitute the following parameters:

• endpoint-name - name of the inference endpoint where the model is deployed

• input.zip - input file

• application/zip - MIME type of the given input file (above)

• result.json - filename where the inference results are written to.

Resources

Sample Notebook

Sample Input

Sample Output

Mphasis DeepInsights
Sample Notebook
Sample Input