Bhavani Ravi
Independent Software Consultant
Chennai, India
Actions
Bhavani Ravi is an Independent Software Consultant specializing in Backend/Data and DevOps. She is an avid open-source contributor, blogger, and voices for diversity in tech spaces
Area of Expertise
Topics
Apache Airflow Bad vs. Best Practices In Production
Apache Airflow - The open-ended nature of this orchestration tool gives room for a variety of customization.
While this is a good thing, there are no bounds in which the system can or cannot be used, resulting in wasting a lot of time in scaling, testing, and debugging when things aren't set properly.
In this talk, we will go through a series of factors that data teams need to keep a watch for while setting up an Airflow system.
- Infrastructure
- Teams and responsibilities
- Development best practices
- Pipeline best practices
- Monitoring and observability
- Fail-proof and recoverable system
Chatbots 101
Workshop Goal:
1. New technologies can be scary but not difficult
2. The idea on what's and why's of chatbot
3. Taste on how easy it is to build one
4. A couple of chatbots that they can show off to others
What Attendees Will Make:
The workshop escalates from something basic to something useful.
1. Chatbot in 5 lines
- echo bot - A bot that repeats you
- Search bot - A google search bot
2. Draw bot - A bot that draws shapes as you tell them(without NLP)
3. Using Chatbot platforms to build a chatbot - Dialogflow/RasaNLU
- Drawbot using NLP
Intro to Topic:
1. What is chatbot?
2. Why a chatbot?
3. Web app vs Chatbot
4. Tools available to build one
5. Demo of few chatbots
Tools/Resources Needed:
Laptops with internet
Python, pycharm setup with necessary packages installed
Machine Learning Behind Chatbots
Description
Have you ever tried building a chatbot? You would definitely start with Dialogflow or IBM Watson or any chatbot framework from these tech giants. As you start building you be curious to understand what’s happening underneath these engines. When the use case hit the real world you will find the importance of understanding these inner workings.
In this talk, we will open the hood of an open-source chatbot framework RasaNLU and understand the components involved and how they contribute to building a chatbot
Audience
The talk is for someone who is curious about chatbot technologies and want to get a deeper understanding of how they work. A bit of python and a few ML beginner videos are enough to get you started building bots.
At the end of the talk, you will have an understanding of how chatbot engines work and how to tackle some of the challenges.
Outline
Chatbot’s architecture (5 mins)
What is Chatbot?
Architecture - A flow Diagram, NLP, NLU
Few Terminologies - Intent, Entities, Actions
ML behind Chatbots (16 mins)
Intent Classification - Given a text how does the chatbot understand whether it should search the DB or Greet back. (5 mins)
Named Entity Extraction - Given a message, say “By me a pepperoni pizza” how does the chatbot know it has to buy “Pizza” and not pasta (5 mins)
Processing pipelines - (5 mins)
Q&A - 4 mins
Previous Talking Experience
https://www.youtube.com/watch?v=ojuq0vBIA-g
Getting Started With Open Source
Open source is the scary dream of most developers. Yes, there are a million resources out there, but nothing can give you the push to actually get started. In the advent of all those failed moments trying to enter the open-source world, I found a mental model of what's required to make that open source contribution
Call it hacks, Quirks, Shortcuts, but what I am going to share is a mental model so that you can also become an open-source contributor for major players like Pandas, Pytorch etc.,
Bhavani Ravi
Independent Software Consultant
Chennai, India
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top