1. AMP: Audiovisual Metadata Platform
2. Documentation
3. For Developers
4. MGM Adapters

• About
  • The AWS Comprehend adapter is a python based tool that takes in speech segmentation JSON as input and produces a list of entities. Each entity contains a start, end, type, label, and score.

• Source Code
  • galaxy/tools/aws/aws_comprehend.xml
    Tool configuration detailing tool execution, input file, output file, and labeling.
  • galaxy/tools/aws/aws_comprehend.py
    Python script to call AWS comprehend via API and conform json to schema
  • galaxy/tools/amp_json_schema/entity_extraction_schema.py
    Set of classes representing the entity extraction schema

• Dependencies

  • Boto3

  • An AWS Bucket

  • An AWS IAM role for Comprehend capable of put/get/list operations on the supplied S3 bucket.  See the following documentation: https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions\

    { "Version": "2012-10-17", "Statement": [ { "Sid": "VisualEditor0", "Effect": "Allow", "Action": [ "s3:PutObject", "s3:GetObject", "s3:ListBucket" ], "Resource": [ "arn:aws:s3:::amp-dev-test/*", "arn:aws:s3:::amp-dev-test" ] } ] }

• Installation:
          $ pip install Boto3

• Running the tool

  • The tool can be invoked from Galaxy UI as other tools. User needs to supply input data in the form of standardized speech to text output

• Parameters

  • $input_file: the speech to text output.

  • $json_file: the output json file.

  • $bucketName: the AWS bucket to store input and output files.  For testing purposes, the bucket amp-dev-test can be used.

  • [$][dataAccessRoleArn: IAM role allowing comprehend to access S3.
    ]

    [
    ]

• Output
  • Json file conforming to schema located here https://wiki.dlib.indiana.edu/display/AMP/MGM---Entity-Extraction

Document generated by Confluence on Feb 25, 2025 10:39