Name: unstructured-text-demo
Owner: Google Cloud Platform
Description: null
Created: 2016-08-12 20:09:34.0
Updated: 2018-01-22 18:47:32.0
Pushed: 2017-09-29 19:13:59.0
Homepage: null
Size: 57
Language: JavaScript
GitHub Committers
User | Most Recent Commit | # Commits |
---|
Other Committers
User | Most Recent Commit | # Commits |
---|
This demo contains code to detect entities and sentiment of a dump of Wikipedia, as well as a webapp that queries the resultant BigQuery table.
This demo is split up into two parts:
tools
directory contains a Google Cloud Dataflow pipeline
that starts from a Wikipedia XML dump and ends with a table in
Google BigQuery containing all detected entities in Wikipedia, by way of
the Google Cloud Natural Language API.app
directory contains a Google App Engine app that uses
Wikipedia's Mediawiki API to fetch a given Wikipedia page
dynamically, and uses the Natural Language API to highlight all the
entities detected. It can also display a related-entities graph, by querying
the BigQuery table created above.For tools/
, see tools/README.md
For app/
:
Install the AppEngine Python SDK
Download a service account key and set the
GOOGLE_APPLICATION_CREDENTIALS
environment variable, as detailed here.
Install the dependencies into a lib/
directory:
$ cd app/
$ pip install -r requirements.txt -t lib/
For tools/
, see tools/README.md
For app/
:
Run the local test server:
$ cd app/
$ dev_appserver.py .
Visit the site at http://localhost:8080/
This is not an official Google product.