Action Items & Follow ups

Enable this model configuration to list all the action items generated from the conversation

Overview

Action Items API detects an event, task, activity, or action that needs to take place in the future (after the conversation). These Action items can be of high priority with a definite assignee and due date or of lower priority with a non-definite due date.

All action items are generated with action phrases, assignees, priority detection, and due dates to make the output immediately consumable by your CRM or project management tools

modelTypeConfiguration

Keys	Value
modelType	action_items
modelConfig	Model Configuration object for action_items

modelConfig parameters

Keys	Possible Values	Default Value
priority	1, 2, 3	1

Priority Values

Value	Description
1	Only high priority questions.
2	High and Medium priority questions.
3	High, Medium and Low priority questions.

Priority Description

Priority	Description
High	Well defined action item with a date attached to it, eg: I will revert back to you on the status of the order by friday.
Medium	Well defined action items that don't have a date attached to them, eg: I will get back to you on the order status
Low	Vaguely defined action items in the call, eg: I'll get back to you on that

Example Request

Curl

curl --location --request POST 'https://api.marsview.ai/cb/v1/conversation/compute' \
--header 'Content-Type: application/json' \
--header "Authorization: {{Insert Auth Token}}" \
--data-raw '{
        "txnId": "{{Insert txn ID}}",
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : true,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":true,
                    "enableTopics":false
                    }
            },
            {
            "modelType":"speech_type_analysis"
            },
            {
            "modelType":"action_items",
            "modelConfig":{
                    "priority": 1
            }
            }
        ]
}'

Python

import requests
auth_token = "replace this with your auth token"
txn_id = "Replace this with your txn id"
request_url = "https://api.marsview.ai/cb/v1/conversation/compute"


def get_action_items():
  payload={
        "txnId": txn_id,
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : True,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":True,
                    "enableTopics":False
                }
            },
            {
            "modelType":"speech_type_analysis"
            },
            {
            "modelType":"action_items"
            }
            ]
        }
  headers = {'authorization': '{}'.format(auth_token)}
  
  response = requests.request("POST", headers=headers, json=payload)
  print(response.text)
  if response.status_code == 200 and response.json()["status"] == "true":
    return response.json()["data"]["enableModels"]["state"]["status"]
  else:
    raise Exception("Custom exception")

if __name__ == "__main__": 
    get_action_items()

Example Response

"data": {
    "actionsData": [
        {
            "actions": "I am willing and capable of working long hours to complete the tasks.",
            "startTime": 79979.999,
            "endTime": 84060,
            "coreferencedAction": "I am willing and capable of working long hours to complete the tasks.",
            "confidence": "0.88245463",
            "priority": "high",
            "completionDate": "NA"
        },
    ]
}

Example Response

Field	Description
actionData	List of actions objects identified in the Video/Audio
actions	Identified sentences inside the given time frame that represent actions
coreferencedActions	Identified sentences inside the given time frame that represent actions
startTime	Start time of the sentence in the input Video/Audio in milliseconds.
endTime	End time of the sentence in the input Video/Audio in milliseconds.
confidence	Model's confidence the the predicted action
priority	Priority of the action item. Defenitions for priority are given in the Priority description table
completionDate	Date specified in the given sentence identified as an action. This value will be null if a date is not mentioned in the sentence