{
"openapi": "3.0.1",
"info": {
"title": "Speakable Summarizer API",
"description": "This API gives you RESTful access to our Speakable Summarizer NLP engine.
The Speakable Summarizer is most suitable for producing fluently readable summaries with broadcast applications in mind (example: for likes of Alexa, Google Assistant). This summarizer's strong suit is to cover the main topic from the input documents, so it is best used in cases where we know that the inputs will have a clear focus. Speakable summaries can be optimized to suit client needs, especially if the client provides editorial guidelines and sufficient training data on which we can optimize.",
"version": "1.0"
},
"servers": [
{
"url": "https://api.agolo.com/speakable-summarizer"
}
],
"paths": {
"/summarization": {
"post": {
"summary": "Summarize",
"operationId": "5dce8bfb7b573e9500dcca2a",
"requestBody": {
"description": "
The POST request body should be a JSON of the following format:
\n{\n \"summary_length_words\": \"<how many approximate words the output summary should contain>\",\n \"articles\": [<Article objects>]\n\n }\n
\nThe Article
objects must have one of the following two formats:
Web article URLs:
\n{ \"url\": \"https://www.reuters.com/article/us-usa-immigration/white-house-softens-tone-after-threat-to-close-border-with-mexico-idUSKCN1RE1PE\" }\n
\n Article title and body in plain text:
\n{\n \"title\": \"An unlikely contender, Sanders takes on ‘billionaire class’ in 2016 bid\",\n \"text\": \"The White House took a step back on Tuesday from a threat to close the U.S. border with Mexico, even as a redeployment of border officers in recent days has led to a slowdown of legal crossings and commerce at U.S. ports of entry there. White House spokeswoman Sarah Sanders said the...\"\n}\n
\n You can perform multi-document summarization by passing multiple article URLs or text in the request body. The algorithm assumes the input articles are about the same topic or story.
If you pass two distinct stories, the summary for that cluster will not be very meaningful. For example, a story about a semiconductor company’s stock falling due to an earthquake and a story about the earthquake itself are related stories but are distinct stories.
Multiple input can be passed in this JSON format:
{\n \"summary_length_words\":\"100\",\n \"articles\":[\n {\n \"url\": \"https://venturebeat.com/2017/05/03/microsoft-invests-in-agolo-a-startup-thats-fighting-information-overload-with-automated-summarizations/\"}\n },\n {\n \"url\": \"https://www.geekwire.com/2017/microsoft-ventures-doubles-ai-new-investments-agolo-bonsai/\"}\n }\n ]\n}
\nA successful response will be a JSON object with the following attributes:
\ntitle
: The title of the summary, if applicable.
sentences
: An array of summary sentences and item metadata, grouped by item. Each element is a Summary
object.