Skip to content

SRS))IBM Watson API with blue mix

strmathSAaD edited this page Nov 13, 2018 · 1 revision

This wiki covers brief explanation of how to use IBM Watson for the project

Environment Setting

There is not a specific dependency for environment setting.

Except for the developing language.

Won't share ID and password since this GitHub repository is a public one.

Supporting methods to use

Curl, Node, Java, Python.

We will use python for the project.

Package Install

pip install --upgrade watson-developer-cloud

Example

 from watson_developer_cloud import NaturalLanguageUnderstandingV1

 natural_language_understanding = NaturalLanguageUnderstandingV1(

      version='{version}',

      iam_apikey='{iam_api_key}'

 )

Check reference for the detail usage.

How to use

HTTP POST/analyze ~> via HTTP request(REST API)

requirement: IBM api token

Integration Point

Retrieve news content data of url address from database or HDFS.

Pricing

Lite(Free)

We will consider only free version, so I will collect 5 tokens of each member.

– Analyze up to 30,000 NLU items per month

– Use with any of the features

– One free custom model

1 NLU item = 1 group of 10,000 characters x 1 feature

An NLU item is based on the number of data units enriched and the number of enrichment features applied. A data unit is 10,000 characters or less. For example: extracting Entities and Sentiment from 15,000 characters of text is (2 Data Units * 2 Enrichment Features) = 4 NLU Items.

Reference

IBM NLP API docs: https://www.ibm.com/watson/developercloud/natural-language-understanding/api/v1/#introduction

IBM NLP API demo: https://natural-language-understanding-demo.ng.bluemix.net/?cm_mc_uid=26819277564015388457338&cm_mc_sid_50200000=53114221539594529205&cm_mc_sid_52640000=58952151539594529209

IBM News Discovery API: https://console.bluemix.net/docs/services/discovery/watson-discovery-news.html#watson-discovery-news

IBM News Discovery API demo: https://discovery-news-demo.ng.bluemix.net


Written by Ilgwon Park

Clone this wiki locally