udacity / aind-nlp-bookworm Goto Github PK

View Code? Open in Web Editor NEW

69.0 16.0 177.0 2.97 MB

A simple question-answering system built using IBM Watson's NLP services.

License: MIT License

Jupyter Notebook 50.51% HTML 45.55% Python 3.95%

aind-nlp-bookworm's Introduction

Project: Bookworm

A simple question-answering system built using IBM Watson's NLP services.

Overview

In this project, you will use IBM Watson's NLP Services to create a simple question-answering system. You will first use the Discovery service to pre-process a document collection and extract relevant information. Then you will use the Conversation service to build a natural language interface that can respond to questions.

Getting Started

Clone this repository to your local computer.

If you have the AIND Anaconda environment prepared, now is a good time to activate it.

Open the notebook bookworm.ipynb from a terminal using the following command:

jupyter notebook bookworm.ipynb

Then follow the instructions in the notebook.

Note: You may have to install some packages (mentioned in the notebook). To do so, simply open another terminal and use pip.

Tasks

Complete each task in the notebook by implementing or modifying code wherever there is a TODO comment in a code cell, and answering any inline questions by modifying markdown cells. E.g.:

Q: What is the overall sentiment detected in this text? Mention the type (positive/negative) and score.

A: Negative, -0.798

Once you have completed all tasks, save the notebook, and then export it into a PDF or HTML. Remember to submit both the notebook (.ipynb) and the PDF/HTML, along with any other files that may be needed, e.g. data files, in case you use your own (sample files provided with the project don't need to be submitted).

Note: Please do not submit your service-credentials.json file - that is meant to be kept secret.

Extensions

Feel free to work on the project with your own dataset. You can also turn it into a web-based application and deploy it on Bluemix.

IBM Watson Resources

Watson Developer Cloud [GitHub]

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.

aind-nlp-bookworm's People

Contributors

Stargazers

Watchers

Forkers

swaption2009 behzadip td2014 spil-peter-forgacs bkrmdahal jcriscione ibratface lxwvictor eakdogan cmiller112000 morganel thirupathipattipaka arunkv bn2302 oroant adrianyi bryantravissmith chriscurrin m7mdbadawy prafsoni danielgf3 brendanvadacorabell rballet javierivanov suribes isallam lxyea helenwang11 mindis chetchita641 xingdu1991 varuna82 kjkhan kposen kvr777 khrm hosseinsey ocefra jkheadley sunsided blcooley xgenadam marianokamp sakyalin voyageth mprilucik ppeiris jrohnke auriml chiajasper axsch twopatient kscharpf vikhhr dinghe gsams20 lukamu kelvinai mylesieong vldslvv recto fnakashima knnaraghi heidekrueger sanvert ravirajadrangi alphara sernle b-squad paulraj lorenzomartino86 nilangparikh lushang abhibisht89 sebasibarguen isemenov2015 lzrdgreen sabau buenayerba maloef sudikhya shshnkg romanroibu sseuraeki husams hchalla taiyeeka juhyung-son texpine emma-oc harshanimmagadda44 calvinalvin tushartuteja rohit-ptl vaishnavimamaledeshpande mokahaiku afcarl dantevito qiqika newenglandml

aind-nlp-bookworm's Issues

Watson Error 415 when creating a collection

# Prepare a collection of documents to use
col, col_id = helper.fetch_object(discovery, "collection", "Story Chunks", environment_id=env_id,
    create=True, create_args=dict(
        environment_id=env_id, configuration_id=cfg_id,
        description="Stories and plots split up into chunks suitable for answering"
    ))

WatsonException: Error: The request failed. Please try again., Code: 415

It worked the previous week. New services with new credentials don't solve the issue.

helper.py needs small update to work with watson_developer_cloud version 1.0

Change the environments line in the following to "environment": "list_environments" in the following snippet. Alternatively, give some guidance on which version of the watson_developer_cloud to install. Reference the repo for the change.

# Methods for each object type
    list_methods = {
        "environment": "list_environments",
        "configuration": "list_configurations",
        "collection": "list_collections",
        "workspace": "list_workspaces"
    }

See this forum post for more info.

The Watson Discovery Service no longer supports Alchemy Language enrichments

When executing the notebook's first test I get the error below:

WatsonException: Error: The Watson Discovery Service no longer supports Alchemy Language enrichments. Update your configuration to use Natural Language Understanding enrichments., Code: 400

https://www.ibm.com/blogs/bluemix/2017/03/bye-bye-alchemyapi/

DecrepationWarning from watson_developer_cloud.DiscoveryV1()

discovery = watson_developer_cloud.DiscoveryV1(
                        version='2018-08-01',
                        url=discovery_creds['url'],
                        iam_apikey=discovery_creds['apikey'])

Throws the following warning:

DeprecationWarning: watson-developer-cloud moved to ibm-watson. To get updates, use the new package.

To follow the instructions and update the notebook ibm-watson and ibm-cloud-sdk-core can be installed with pip and imported as follows:

import ibm_watson
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

By using IAMAuthenticator discovery can be instantiated:

authenticator = IAMAuthenticator(apikey=discovery_creds['apikey'],
                                                       url=discovery_creds['url'])
discovery = ibm_watson.DiscoveryV1(version='2018-08-01',
                                                              authenticator=authenticator)

However, both listing and creating environments now throws an error:

environments = discovery.list_environments().get_result()
ApiException: Error: Not Found, Code: 404

and

# Prepare an environment to work in
env, env_id = helper.fetch_object(
    discovery, "environment", "Bookworm",
    create=True, create_args=dict(
        description="A space to read and understand stories"  # feel free to edit
    ))

ApiException: Error: Not Found, Code: 404

udacity / aind-nlp-bookworm Goto Github PK

aind-nlp-bookworm's Introduction

Project: Bookworm

Overview

Getting Started

Tasks

Extensions

IBM Watson Resources

aind-nlp-bookworm's People

Contributors

Stargazers

Watchers

Forkers

aind-nlp-bookworm's Issues

Watson Error 415 when creating a collection

helper.py needs small update to work with watson_developer_cloud version 1.0

The Watson Discovery Service no longer supports Alchemy Language enrichments

DecrepationWarning from watson_developer_cloud.DiscoveryV1()

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent