Build a ChatBot in 10 minutes!
- 1. Build a ChatBot in 10 Minutes! Serverless Summit 2017, Bangalore @dwmkerr #inserverless Dave Kerr Senior Expert, McKinsey & Company
- 3. Thank-you to the organisers and sponsors!
- 5. I am a technology consultant. @dwmkerr #inserverless
- 7. Which is closer to this¡ @dwmkerr #inserverless
- 9. What am I going to talk about? @dwmkerr #inserverless
- 10. Chatbots! @dwmkerr #inserverless Perfect for serverless technology. Today is about fun, not ROI!
- 11. ¡I¡¯ve got to come clean about something¡ @dwmkerr #inserverless
- 12. ¡I know almost nothing about chatbots! @dwmkerr #inserverless
- 13. Lawrence Hunt, Selin Lanzafame, Dave Kerr
- 15. ¡°Amazon Lex is an AWS service for building conversational interfaces for any applications using voice and text. With Amazon Lex, the same conversational engine that powers Amazon Alexa is now available to any developer, enabling you to build sophisticated, natural language chatbots into your new and existing applications. Amazon Lex provides the deep functionality and flexibility of natural language understanding (NLU) and automatic speech recognition (ASR) so you can build highly engaging user experiences with lifelike, conversational interactions, and create new categories of products.¡± @dwmkerr #inserverless
- 17. Let¡¯s see it in action! @dwmkerr #inserverless
- 18. Demo 1: Get a boring-bot running https://github.com/dwmkerr/lex-starter-kit refs/heads/demo1 @dwmkerr #inserverless
- 19. We setup the project with make setup @dwmkerr #inserverless
- 20. We can deploy lex models with make deploy
- 21. Here¡¯s how our conversation looks so far @dwmkerr #inserverless
- 23. Most conversations need input! @dwmkerr #inserverless
- 24. Demo 2: Getting Input with Slots https://github.com/dwmkerr/lex-starter-kit refs/heads/demo2 @dwmkerr #inserverless
- 25. We configure the environment with make config
- 26. We can deploy lex models with make deploy
- 27. Our conversation flow is now more complete
- 28. Cool kids use the shell for everything github.com/dwmkerr/effective-shell @dwmkerr #inserverless
- 30. Using sessions to manage conversation state @dwmkerr #inserverless
- 31. Sometimes we have state which we build up over a conversation¡ @dwmkerr #inserverless
- 32. Demo 3: Sessions https://github.com/dwmkerr/lex-starter-kit refs/heads/demo3 @dwmkerr #inserverless
- 33. Use the session to persist conversation state between intents
- 34. This gets complex! When do you clear a session? At least you save time on the scripting ? @dwmkerr #inserverless
- 35. Bootstrap your bots, and join in for the next set of features! github.com/dwmkerr/lex-starter-kit github.com/dwmkerr/lex-chat @dwmkerr #inserverless
- 38. Tips and Tricks ? Question marks in intent utterances will break Lex! ? Train with realistic data ? Complicated or very variable slots are very hard to work with (e.g. sentences), consider using cards ? Encrypt sensitive environment variables such as keys when using lambda functions @dwmkerr #inserverless
Editor's Notes
- #7: I do three things: Advise on strategy, typical McKinsey stuff Lead our engineering practice A lot of coding
- #8: Lessons Learned: 2 mins 23/25 mins You cannot simply transplant existing projects onto a platform like kubernetes and expect it to scale. Anecdote: a week of time lost while the team try and get a complex multi-database solution working on Kubernetes, a day to run it on VMs. Lesson: Know what works. Stateless, or self organising homogenous nodes
- #9: 5m mark: Serving clients across the world, deploying in airports, writing code.
- #19: Show the readme Setup the environment variable Create the infrastructure Show the bucket and function Show the lambda function, no invocations Show the role and policy, you¡¯ll be glad you have it!
- #24: Demo: 0. show the README and table show how there is a makefile in each project run the first two makefiles Show the circle file Show the travis file
- #30: Show the readme Setup the environment variable Create the infrastructure Show the bucket and function Show the lambda function, no invocations Show the role and policy, you¡¯ll be glad you have it!
- #33: Demo: 0. show the README and table show how there is a makefile in each project run the first two makefiles Show the circle file Show the travis file
- #37: Lessons Learned: 2 mins 23/25 mins You cannot simply transplant existing projects onto a platform like kubernetes and expect it to scale. Anecdote: a week of time lost while the team try and get a complex multi-database solution working on Kubernetes, a day to run it on VMs. Lesson: Know what works. Stateless, or self organising homogenous nodes
- #39: Show the readme Setup the environment variable Create the infrastructure Show the bucket and function Show the lambda function, no invocations Show the role and policy, you¡¯ll be glad you have it!