Presentation on how to chat with PDF using ChatGPT code interpreter
Cognitive workshop series nlu, nlc
1. Naiyarah Hussain
Aoun Lutfi
Worood Dabbas
Alexander Al Basosi
IBM Developer Advocates
COGNITIVE WORKSHOP
SERIES:
Natural Language
Understanding
Natural Language Classifier
3. Watson / Presentation Title / Date3
Our Goals
In this series, we want to
focus on the Watson
services that allow you to
customize functionality to
better fit your use case and
industry
4. With Watson:
You can analyze and interpret all of your data, including unstructured text,
images, audio and video. You can provide personalized recommendations by
understanding a user's personality, tone, and emotion. You can utilize machine
learning to grow the subject matter expertise in your apps and systems. You can
create chat bots that can engage in dialog.
5. With Watson:
You can build cognition into your apps and products, whether it’s a web or native
app, or even robotics.
Watson is available as a set of open APIs
through Bluemix.
https://www.ibm.com/watson/developer/
6. Introducing:
Bringing together infrastructure and platform services, Bluemix is the home of 130+ unique
services, including offerings like IBM Watson and Weather.com, and millions of running
applications, containers, servers, and more.
A platform for the world’s ideas
7. Introducing:
Used by over a million developers making over a billion API calls a day and starting over a
100,000 apps a month. Welcoming over 2,000 new users everyday to the largest Cloud
Foundry deployment. You can join now at bluemix.net.
A platform for the world’s ideas
8. 8
Our Goals:
Today, we'll be showing you
our Natural Language
Understanding & Natural
Language Classifier
services
9. 9
With Watson
The Natural Language Classifier service understands the intent behind text and returns a
corresponding classification, complete with a confidence score. For example “What is the
weather like today? or “Is it hot out?” or “Is it going to be nice today?” are all ways of asking
about “temperature”. Use NLC to answer questions in a contact center, create chatbots,
categorize volumes of written content and more.
Natural Language Classifier
10. 10
With Watson
Analyze text to extract meta-data from content such as concepts, entities, keywords,
categories, sentiment, emotion, relations, semantic roles, using natural language
understanding. With custom annotation models developed using Watson Knowledge
Studio, identify industry/domain specific entities and relations in unstructured text.
Natural Language Understanding
11. Watson / Presentation Title / Date11
Hands on Lab
overview/architecture
The demo takes in an essay then extracts keywords using Watson’s natural language
understanding. Then these keywords are summarized and passed on to a natural language
classifier to classify and categorize it into a Hogwarts House.
Hogwarts
House
Harry Potter Sorting-Hat
12. Watson / Presentation Title / Date12
Hands on Lab
What you need
Download the ZIP file found in:
https://github.com/aounlutfi/go-find-yourself
13. Watson / Presentation Title / Date13
Hands on Lab
overview/architecture
The demo takes in an essay or a social media link then extracts keywords and skill using
Watson’s natural language understanding. Then these skills and keywords are summarized
and passed on to a natural language classifier to classify the summary into a career path.
career
path
Go Find yourself
14. Watson / Presentation Title / Date14
Hands on Lab
What you need
Download the ZIP file found in:
https://github.com/aounlutfi/go-find-yourself
Build with Watson:
Enable cognitive computing features in your app using IBM Watson's Language, Vision, Speech and Data APIs.
https://www.ibm.com/watson/developercloud/doc/common/getting-started-sdks.html
So what is Watson today?
Watson APIs are delivered on a cloud-based, open platform, and with Watson, you can build cognition into your digital applications, products, and operations, using any one or combination of available APIs.
Each API is capable of performing a different task, and in combination, they can be adapted to solve any number of business problems or create deeply engaging experiences.
And we continue to add new and expanded cognitive capabilities to the platform.
The natural language processing (NLP) API family enables users to interact with systems and devices using simple, human language. NLP helps solutions understand the intent of human language by correlating it with other sources of data to put it into context in specific situations.
The machine learning Watson API family helps automate data processing and continually monitor new data and user interactions to rank data and results based on learned priorities. Machine learning can be applied to virtually any data coming from devices and sensors to automatically understand the current conditions, what’s normal, expected trends, properties to monitor and suggested actions when an issue arises.
The video and Image analytics API family enables monitoring of unstructured data from video feeds and image snapshots to identify scenes and patterns. This knowledge can be combined with machine data to gain a greater understanding of past events and emerging situations.
The text analytics API family enables mining of unstructured textual data including transcripts from customer call centers, maintenance technician logs, blog comments and tweets to find correlations and patterns in these vast amounts of data.
through use of the REST APIs for Watson, you can develop a cognitive application in virtually any programming language, and the SDK's enable you to develop your application using natural, language native classes and interfaces for the supported languages
Enable cognitive computing features in your application using IBM Watson’s Language, Vision, Speech, and Data APIs (via IBM Bluemix)
Each service provides:
A REST API and reference docs with code samples for each function
Robust documentation, including an overview and tutorial(s)
A demo application, including a link to the source in GitHub
The following Software Development Kits (SDKs) are available:
Node, Java, Python, iOS, Unity
https://www.ibm.com/watson/developercloud/doc/common/getting-started-sdks.html
open-standards, cloud-based platform
building, managing and running apps
web, mobile and smart devices
developers can choose among various services and tools in order to quickly build engaging solutions.
4 compute models – Virtual servers, containers, CF runtimes/apps, OpenWhisk
The IBM Watson™ Visual Recognition service uses deep learning algorithms to analyze images for scenes, objects, faces, and other content. The response includes keywords that provide information about the content.
A set of built-in classes provides highly accurate results without training. You can train custom classifiers to create specialized classes. You can also create custom collections of your own images, and then upload an image to search the collection for similar images.
The Watson Visual Recognition API is an intelligent system that uses image recognition to identify and tag objects from images. This Watson service has built-in default classifiers that can detect common objects, as well as things within an image, that are recognized or associated with in people’s daily lives.