I would like to use Bluemix to create an IBM Watson search engine (i.e. similar to a Google Search Engine interface) that will query either the internet (websites I specify) or online database and provide summaries of unstructured data, identify concepts, etc.
Are there any existing apps like this available or does anyone know how this can be setup with Bluemix or another platform?
You should take a look at the Alchemy API service on Bluemix.
It allows you to do things like extract entities and keywords.
Most of the APIs allow you to feed them html, text or web-based content. Stringing a bunch of these together and tagging content in a database such as Elasticsearch should allow you to achieve what you're after.
Hard to be too specific given the fairly broad nature of your question.
Related
I'm doing a small project that I don't know how-to connect IBM Watson with Django backend and even looking for the docs: I can't find examples, documentation or tutorials.
Basically, I want to create Jobs (Notebooks running) remotely, but I need to send an ID to each notebook because when I run a notebook I need to specify which file are going to process from Cloud Storage ("MY-PROJECT-COS"). The situation shown in the Figure below describes that.
The pipeline that I want to implement is like the Figure below. And this problem just stopped the whole project. I will really appreciate any suggestion, recommendations and solutions.
You should check the Watson Data APIs. Especially, Create a job and Start a run for a job API calls. Use the request body to pass the specific ID.
You can use a collection of Watson Data REST APIs associated with
Watson Studio and Watson Knowledge Catalog to manage data-related
assets and connections in analytics projects and catalogs on IBM Cloud
Pak for Data.
Catalog data Use the catalog and asset APIs to create catalogs to
administer your assets, associate properties with those assets, and
organize the users who use the assets. Assets can be notebooks or
connections to files, database sources, or data assets from a
connection.
Govern data Use the governance and workflows APIs to implement data
policies and a business glossary that fits to your organization to
control user access rights to assets and to uncover data quality and
data lineage.
Add and find data Use the discovery, search, and connections APIs to
add and find data within your projects and catalogs.
You can also access a local version of this API docs on each Cloud Pak
for Data installation:
https://{cpd_cluster_host}/data-api/api-explorer
I am a new bee to IBM Watson. I went through videos to create virtual assistant/chatbot where we could define intents/entities and answer accordingly. This seems fine when I have limited number of intents/entities. But say, I have a eBook and I want to train Watson to answer from this eBook. How do I achieve this. Anyone high level approach or direction will be really helpful.
There are different approaches.
You could use the integrated search skill which provides a link to Watson Discovery. You would upload your eBook to Watson Discovery and kind of index it.
Another approach is to use a database or something else as backend. Based on the input which identifies the search term and scopes which eBook to search, the answer would be retrieved from the backend database. This tutorial features a Db2 database and Watson Assistant retrieves the answer from the database. A similar approach is taken in this sample which shows how to retrieve excerpts from Wikipedia.
A POC in our project uses IBM Watson Discovery services hosted in cloud for natural language analysis but our company wants an on premise solution for natural language analysis instead of cloud based one.
Is it possible to replace IBM Watson discovery API completely with IBM Watson Explorer.
I did some research and found that Explorer does not have Node JS APIs.
Also IBM Watson Explorer Rest API can be used for simpler use cases like searching.
Please help me in this regard as my knowledge on these two tools is limited.
To answer your question in short, yes it can be done.
Watson Explorer does have an API interface and yes it can be integrated with Node JS as well, it does not have a native npm package...I personally have implemented a very complex solution for a very reputed an automotive client using WEX as the Backend and Data Ingestion engine and Node JS on top, acting as the orchestrator and the UI.
You may want to see this post: https://developer.ibm.com/answers/questions/259089/rest-apis-for-wex-search/
> On Linux: {hostname}/vivisimo/cgi-bin/velocity?v.app=api-run
> Windows : {Hostname }/vivisimo/cgi-bin/velocity.exe?v.app=api-run
The api-runner have all the api's listed and one can also test them against the search collections (search collections are the equivalent to a table where the data is ingested and there are a lot of custom configurations which can be applied to make use of, for advance use).
So for using WEX with Node JS, you can make use of the api-runner url's and directly query WEX Engine.
This is how a sample GET query url may look like:
var link1 = 'http://' + WEX_IP + ':9080/vivisimo/cgi-bin/velocity?v.function=query-search&v.username='+username+'&v.password='+password+'&v.app=api-rest&v.indent=true&sources=' + WEX_col_name + '&start=0&num=15&v.app=api-rest&query=sortby:sort_severity%20AND%20sortby:Create_Date_desc%20AND%20Create_Date:>=03/30/2018%20AND%20case_flag:1%20AND%20NOT%20case_flag:0'
Hope this helps.
PS: The WEX API's return data in xml format, so if one is comfortable in xml parsing, one can use that or as in my case, I used xml2json package on node to covert xml to json object and then parse that to display the required fields on the UI.
I'm Cococa programmer, but right now I encountered situation when I can't go any further without smarter people:)
I always used small databases in my applciations. I programmed PHP backend on my own server and it worked good.
Right now I have to switch for something much bigger and I decided to try with Google App Engine, because it is relatively cheap and has great scalability.
I'm so confused with documentation and I really don't know where to start.
My new app will store data (images, videos) as well as database (mysql) in google cloud.
I concluded that for app like that I should use:
Google Cloud Storage for images / viedos etc.
Google Cloud SQL for CRUD operations for users (inserting and fetching personal data)
I would prefer to use JSON api. Then I don't have to write any Java, Python or GO code, right? Only REST requests for Google Cloud SQL...
My question is : Am I thinking correctly? Should I use these two services?
Google App Engine has a feature called "Cloud Endpoints" (Java | Python)
that automatically generates a JSON API similar to the APIs that Google provides for its own services (and also generates client libraries in JavaScript, Obj-C, and Java to invoke those APIs), saving you the trouble of writing the REST API yourself and manually serializing/deserializing the request and, instead, focusing on just the business logic that performs the storage and retrieval operations. So, what I would suggest is that you write the code that reads/writes data into the datastore (and cloud storage), but then use Cloud Endpoints to automatically generate your JSON API and client libraries, rather than manually writing that code.
Your plan seems fine so far. Google Cloud Storage is a great choice for storing a large number of images and movies, and Google Cloud SQL is a great choice for handling smaller, more relational data.
If you're using PHP from app engine, there's built-in support for Google Cloud Storage. See https://developers.google.com/appengine/docs/php/googlestorage/
If you're using PHP from your app that lives somewhere else, you could write to the Google Cloud Storage JSON or XML APIs directly, but there's also a PHP library for the Google APIs that might be easier for you to use: https://code.google.com/p/google-api-php-client/
In search of a 'Cloud Content Management System' like http://osmek.com/,
I could not find a single other CCMS that does what I want it to do :)
Basically, what I need is content management without a website frontend attached.
Just basic storage of data, documents, images, etc. etc. with a simple API to access, like Osmek. Just NoSQL or SQL based services won't do, because there can be images or documents attached. And, ofcourse, I'd like to have a backend to manage the data (like a typical CMS does) without writing a backend myself (if it's just the service)
Osmek is great, and it works most awesome in conjunction with Actionscript 3, but I'm just looking / searching for alternatives (if there even are any yet).
I need this form of hosted content management for content-manageing a mobile application.
So the question is: Is there anything else out there that does the same as osmek that you know of? OR, how do you manage application specific content?
Thanks!
I'd encourage you to take a look at Cloud CMS (http://www.cloudcms.com).
Cloud CMS is a JSON content management (CMS) platform built on top of MongoDB with a REST API and drivers for a variety of languages. You just drop in a driver and call methods to query, create, update and delete content.
The platform provides everything you need to power the back-end for mobile and HTML5 applications - from managing your content to managing users and groups, credentials, security tokens (OAuth2), Git-like collaborative workspaces, real-time analytics, activities, data transformations and more.
Everything runs in the cloud on an elastic back-end. It's probably more akin to Parse than a traditional CMS. You just make calls to the APIs. We keep the costs low by letting you only pay for what you use (almost like a utility). You just pay for storage and data transfer.
Disclaimer: I'm one of the founders of Cloud CMS. So I'm a pretty lousy reference in terms of its objective value. However, a couple of us worked at traditional "ECM" companies in the past and we think we've built something that puts a genuine beating on those guys.