SlideShare ist ein Scribd-Unternehmen logo
1 von 34
Your Next App Might Just Be A Bot:
Building Conversational Bots with Python
PyCon Nigeria | David Asamu
about.me/david_asamu
Before we get
started
Here is why you
should pay attention
Interesting Statistics
● 25% of installed apps are never used.
● The average Android app loses 77% of its daily active users
within the first 3 days.
- Google's consumer marketing insight
What is the implication of
the stats above?
Apps trying to get to
the user’s home
screen
More Interesting Statistics
● Just Yesterday, after we kicked off the conference, Facebook announced that
Messenger now has 1.3 billion active monthly users
● Whatsapp has 1.3 billion active monthly users as well
● 30% of all time spent online is now allocated to social media interaction
● By 2020, over 80% of businesses are expected to have some sort of chatbot
automation implemented (Business Insider, 2016)
Bot Statistics
WAIT FOR IT …..
Why your Business needs a bot
In the coming years, with the
rise of general purpose
assistants, bots will
eventually be in the fabric of
everything, not just in
Messaging Apps.
What is a bot
anyway?
Building
Conversational
Agents
CONVERSATIONAL ENGINE
1 2 3
A. what to do before you start coding
● Understand precisely the role of the bot, make a list of service
● Read the documentation of the platform
● understand what is possible, what is not
How to set up the
project?
A. Pick the right tools
B. what should your
project structure look
like?
● webhook
● engine
● response handler
What to do next?
1. Break your idea into services
A service is a broad classification of the user requests
your bot would be able to handle. For an e-commerce
company, services could include commerce service,
user complaint service, FAQs service, etc
2. Guidelines for writing services
● A service should be simple enough to describe in a
sentence.
● A service must not be ambiguous, it should have one
and only one meaning
3. Describe each service using intents
Services can further be broken down using intents to
zero-in on exactly what the user wants.
Matching the right intent is very important as this
determines what data to expect/request from the user
and when the conversation can be marked as complete
4. Train a classifier to recognize intents
and services
● Get quality data set for training
● Learn from user interaction
5. Extract Entities and Parameters
● This involves going from sentences to structured data that can serve as
inputs to other systems or microservices.
● Use natural language processing to get names, addresses, time and other
entities of interest.
● Take advantage of suggested responses
● Use slot-filling to handle incomplete request from the user
6. Build a webhook for fulfilment
● After a complete user interaction, the user request has to be processed.
● This typically involves setting up a Rest API
● The API handles fulfilments such as saving the extracted data to the
database, feeding the data to other systems as well as triggering other
independent services, or even a physical action such as a man delivering
pizza.
How to go about it?
Start Small,
iterate
CHALLENGES
Scaling
Handling Big Data
Getting quality data
for training
CONCLUSION
Understanding what’s possible and what isn’t with today’s AI and machine
learning capabilities is key for anyone looking to use such technology to build
or enhance applications. If you’re not skeptical enough about claims being
made about current capabilities, you could waste enormous amounts of time
and money trying to do something that can’t (yet) be done. On the other
hand, if you’re too skeptical, you risk missing opportunities to deploy today’s
AI tech in incredibly useful and profitable ways
Source - TechCrunch
THANK YOU!
Questions and Answer
Sessions
(Go easy on me!)

Weitere ähnliche Inhalte

Ähnlich wie Building Conversational Bots with Python

Product Launch Portfolio.pdf
Product Launch Portfolio.pdfProduct Launch Portfolio.pdf
Product Launch Portfolio.pdfJOHNADEMILUYI3
 
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEM
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEMINTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEM
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEMIRJET Journal
 
Intranet Project: Roll-out Strategy & Pain Points to consider
Intranet Project: Roll-out Strategy & Pain Points to considerIntranet Project: Roll-out Strategy & Pain Points to consider
Intranet Project: Roll-out Strategy & Pain Points to considereXo Platform
 
Top .NET development companies to outsource
Top .NET development companies to outsourceTop .NET development companies to outsource
Top .NET development companies to outsourceMindfire LLC
 
8 Step to Build Your lot-Based Mobile Parking System.pdf
8 Step to Build Your lot-Based Mobile Parking System.pdf8 Step to Build Your lot-Based Mobile Parking System.pdf
8 Step to Build Your lot-Based Mobile Parking System.pdfExpert App Devs
 
HealthCare ChatBot Using Machine Learning
HealthCare ChatBot Using Machine LearningHealthCare ChatBot Using Machine Learning
HealthCare ChatBot Using Machine LearningIRJET Journal
 
What to decide before going in for an intranet
What to decide before going in for an intranetWhat to decide before going in for an intranet
What to decide before going in for an intranetSridutt YS
 
IRJET - Interaction based Expert System
IRJET -  	  Interaction based Expert SystemIRJET -  	  Interaction based Expert System
IRJET - Interaction based Expert SystemIRJET Journal
 
Ai app development venkat vajradhar - medium
Ai app development   venkat vajradhar - mediumAi app development   venkat vajradhar - medium
Ai app development venkat vajradhar - mediumvenkatvajradhar1
 
Data analytic for mobile app development
Data analytic for mobile app developmentData analytic for mobile app development
Data analytic for mobile app developmentTrieu Nguyen
 
Data Analytics for Mobile App Development
Data Analytics for Mobile App DevelopmentData Analytics for Mobile App Development
Data Analytics for Mobile App DevelopmentBarcamp Saigon
 
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AI
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AIIIBA® Brisbane - The Rise of ChatGPT, Chatbots and AI
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AIAustraliaChapterIIBA
 
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMSBANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMSIRJET Journal
 
Integrating Bots into your Digital Workplace Strategy #spsne
Integrating Bots into your Digital Workplace Strategy #spsneIntegrating Bots into your Digital Workplace Strategy #spsne
Integrating Bots into your Digital Workplace Strategy #spsneKanwal Khipple
 

Ähnlich wie Building Conversational Bots with Python (20)

Internship report
Internship reportInternship report
Internship report
 
IRJET- Helping Hand
IRJET- Helping HandIRJET- Helping Hand
IRJET- Helping Hand
 
Product Launch Portfolio.pdf
Product Launch Portfolio.pdfProduct Launch Portfolio.pdf
Product Launch Portfolio.pdf
 
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEM
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEMINTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEM
INTELLIGENT CHATBOT FOR COLLEGE ENQUIRY SYSTEM
 
Intranet Project: Roll-out Strategy & Pain Points to consider
Intranet Project: Roll-out Strategy & Pain Points to considerIntranet Project: Roll-out Strategy & Pain Points to consider
Intranet Project: Roll-out Strategy & Pain Points to consider
 
Top .NET development companies to outsource
Top .NET development companies to outsourceTop .NET development companies to outsource
Top .NET development companies to outsource
 
8 Step to Build Your lot-Based Mobile Parking System.pdf
8 Step to Build Your lot-Based Mobile Parking System.pdf8 Step to Build Your lot-Based Mobile Parking System.pdf
8 Step to Build Your lot-Based Mobile Parking System.pdf
 
JIT Project
JIT ProjectJIT Project
JIT Project
 
HealthCare ChatBot Using Machine Learning
HealthCare ChatBot Using Machine LearningHealthCare ChatBot Using Machine Learning
HealthCare ChatBot Using Machine Learning
 
What to decide before going in for an intranet
What to decide before going in for an intranetWhat to decide before going in for an intranet
What to decide before going in for an intranet
 
IRJET - Interaction based Expert System
IRJET -  	  Interaction based Expert SystemIRJET -  	  Interaction based Expert System
IRJET - Interaction based Expert System
 
Ai app development venkat vajradhar - medium
Ai app development   venkat vajradhar - mediumAi app development   venkat vajradhar - medium
Ai app development venkat vajradhar - medium
 
Rajput Bandhu
Rajput BandhuRajput Bandhu
Rajput Bandhu
 
Data analytic for mobile app development
Data analytic for mobile app developmentData analytic for mobile app development
Data analytic for mobile app development
 
Data Analytics for Mobile App Development
Data Analytics for Mobile App DevelopmentData Analytics for Mobile App Development
Data Analytics for Mobile App Development
 
Does your Business Really Need a Mobile App?
Does your Business Really Need a Mobile App?Does your Business Really Need a Mobile App?
Does your Business Really Need a Mobile App?
 
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AI
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AIIIBA® Brisbane - The Rise of ChatGPT, Chatbots and AI
IIBA® Brisbane - The Rise of ChatGPT, Chatbots and AI
 
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMSBANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS
BANKING CHATBOT USING NLP AND MACHINE LEARNING ALGORITHMS
 
Integrating Bots into your Digital Workplace Strategy #spsne
Integrating Bots into your Digital Workplace Strategy #spsneIntegrating Bots into your Digital Workplace Strategy #spsne
Integrating Bots into your Digital Workplace Strategy #spsne
 
How Chat GPT Helping Mobile App Businesses.pdf
How Chat GPT Helping Mobile App Businesses.pdfHow Chat GPT Helping Mobile App Businesses.pdf
How Chat GPT Helping Mobile App Businesses.pdf
 

Kürzlich hochgeladen

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 

Kürzlich hochgeladen (20)

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 

Building Conversational Bots with Python

  • 1. Your Next App Might Just Be A Bot: Building Conversational Bots with Python PyCon Nigeria | David Asamu about.me/david_asamu
  • 3. Here is why you should pay attention
  • 4. Interesting Statistics ● 25% of installed apps are never used. ● The average Android app loses 77% of its daily active users within the first 3 days. - Google's consumer marketing insight
  • 5. What is the implication of the stats above?
  • 6. Apps trying to get to the user’s home screen
  • 7. More Interesting Statistics ● Just Yesterday, after we kicked off the conference, Facebook announced that Messenger now has 1.3 billion active monthly users ● Whatsapp has 1.3 billion active monthly users as well ● 30% of all time spent online is now allocated to social media interaction ● By 2020, over 80% of businesses are expected to have some sort of chatbot automation implemented (Business Insider, 2016)
  • 9. WAIT FOR IT …..
  • 10.
  • 11. Why your Business needs a bot
  • 12. In the coming years, with the rise of general purpose assistants, bots will eventually be in the fabric of everything, not just in Messaging Apps.
  • 13.
  • 14. What is a bot anyway?
  • 15.
  • 16.
  • 19. A. what to do before you start coding ● Understand precisely the role of the bot, make a list of service ● Read the documentation of the platform ● understand what is possible, what is not
  • 20. How to set up the project?
  • 21. A. Pick the right tools
  • 22. B. what should your project structure look like? ● webhook ● engine ● response handler
  • 23. What to do next?
  • 24. 1. Break your idea into services A service is a broad classification of the user requests your bot would be able to handle. For an e-commerce company, services could include commerce service, user complaint service, FAQs service, etc
  • 25. 2. Guidelines for writing services ● A service should be simple enough to describe in a sentence. ● A service must not be ambiguous, it should have one and only one meaning
  • 26. 3. Describe each service using intents Services can further be broken down using intents to zero-in on exactly what the user wants. Matching the right intent is very important as this determines what data to expect/request from the user and when the conversation can be marked as complete
  • 27. 4. Train a classifier to recognize intents and services ● Get quality data set for training ● Learn from user interaction
  • 28. 5. Extract Entities and Parameters ● This involves going from sentences to structured data that can serve as inputs to other systems or microservices. ● Use natural language processing to get names, addresses, time and other entities of interest. ● Take advantage of suggested responses ● Use slot-filling to handle incomplete request from the user
  • 29. 6. Build a webhook for fulfilment ● After a complete user interaction, the user request has to be processed. ● This typically involves setting up a Rest API ● The API handles fulfilments such as saving the extracted data to the database, feeding the data to other systems as well as triggering other independent services, or even a physical action such as a man delivering pizza.
  • 30. How to go about it?
  • 32. CHALLENGES Scaling Handling Big Data Getting quality data for training
  • 33. CONCLUSION Understanding what’s possible and what isn’t with today’s AI and machine learning capabilities is key for anyone looking to use such technology to build or enhance applications. If you’re not skeptical enough about claims being made about current capabilities, you could waste enormous amounts of time and money trying to do something that can’t (yet) be done. On the other hand, if you’re too skeptical, you risk missing opportunities to deploy today’s AI tech in incredibly useful and profitable ways Source - TechCrunch
  • 34. THANK YOU! Questions and Answer Sessions (Go easy on me!)