Abstractive Summary

This API will summarize your conversation building new information based on the conversation.

Overview

Abstractive summary generation rewrites the entire document by building internal semantic representation, and then a summary is created using natural language processing.

Source: Medium

Input Type Supported: Audio, Text

Model Dependency: Speech to Text, Speaker Separation, Extractive summary

post
Compute Metadata

https://api.marsview.ai/v1/conversation/compute
This method is used to upload an audio or video file on which metadata has to be computed. Settings object can be used to enable/disable metadata from different models. Check the overview section for getting a list of models that are available
Request
Response
Request
Headers
appSecret
required
string
<sample-app-secret>
appId
required
string
<sample-app-Id>
Content-Type
optional
string
application/json
Body Parameters
abstractive_summary.enable
required
boolean
Extractive summary will be computed when abstractive_summary.enable key is set to true under the settings object
Response
200: OK
A Transaction ID is returned in the JSON body once the processing job is launched successfully. This Transaction ID can be used to check the status of the job or fetch the results of the job once the metadata is computed
{
"status":true,
"transaction_id":32dcef1a-5724-4df8-a4a5-fb43c047716b,
"message": " Compute job for file-id: 32dcef1a-5724-4df8-a4a5-fb43c047716b launched successfully"
}
400: Bad Request
This usually happens when the settings for computing the metadata are not configured correctly. Check the request object and also the dependencies required to compute certain metadata objects. ( For Example: Speech to Text has to be enabled for Action Items to be enabled)
{
"status":false,
"error":{
"code":"MCST07",
"message":"DependencyError: emotion_analysis depends on speech_to_text"
}
}

Example API Call

Request

CURL
CURL
curl --request POST 'https://api.marsview.ai/v1/conversation/compute' \
--header 'appSecret: 32dcef1a-5724-4df8-a4a5-fb43c047716b' \
--header 'appId: 1ZrKT0tTv7rVWX-qNAKLc' \
--header 'Content-Type: application/json' \
--data-raw '{
"settings":{
"speech_to_text":{
"enable":true,
"pii_detection":false,
"custom_vocabulary":["Marsview" , "Pikachu"]
},
"speaker_separation":{
"enable":true,
"num_speakers":4
},
"extractive_summary":{
"enable":true
},
"abstractive_summary":{
"enable":true
}
}
}'

Response

Given below is a sample response JSON when the Status code is 200.

{
"status":true,
"transaction_id":32dcef1a-5724-4df8-a4a5-fb43c047716b,
"message": " Compute job for file-id: 32dcef1a-5724-4df8-a4a5-fb43c047716b launched successfully"
}

post
Request Metadata

https://api.marsview.ai/v1/conversation/fetch
This method is used to fetch specific Metadata for a particular file_id. It can also be used for long polling to track the progress of compute under the status object.
Request
Response
Request
Headers
Content-Type
optional
string
application/json
appId
optional
string
<sample-app-id>
appSecret
optional
string
<sample-app-secret>
Body Parameters
fileID
optional
string
fileId of the audio/video file
data.extractive_summary
optional
boolean
Returns extractive summary for file_id once computed
Response
200: OK
The output consists of two objects. The data object returns the requested metadata if it is computed. The status object shows the current state of the requested metadata. Status for each metadata field can take values "Queued"/"Processing"/"Completed". Shown below is a case where "abstractive summary" Job is in "Queued" state and "Completed" state.
QUEUED STATE
COMPLETED STATE
QUEUED STATE
{
"status":{
"abstractive_summary":"Queued",
}
"data":{
"abstractive_summary":{}
}
}
COMPLETED STATE
{
"status":{
"abstractive_summary":"Completed"
}
"data":{
"abstractive_summary":{
"text":"A watch is a portable timepiece intended to be carried or worn by a person. It is designed to keep a consistent movement despite the motions caused by the person's activities. A wristwatch is designed to be worn around the wrist, attached by a watch strap or other type of bracelet, including metal bands, leather straps or any other kind of bracelet. A pocket watch is designed for a person to carry in a pocket, often attached to a chain. The study of timekeeping is known as horology. Watches progressed in the 17th century from spring-powered clocks, which appeared as early as the 14th century. During most of its history the watch was a mechanical device, driven by clockwork, powered by winding a mainspring, and keeping time with an oscillating balance wheel.",
"confidence":0.82
}
}
}

Response Object Fields

Fields

Description

text

Summarized paragraph generated from Marsview generated Transcript

confidence

Confidence of the Abstractive summary (Ranges from 0 to 1)