2020 : Bots are back..

NOTES:

Master Reference — Github Page (link)

🔬 Lab Exercise (link) — 2 hours

An Intro to script writing (link)

Chatbot Datasets (link)

Demo(link)

Essentials

Slides (Intro) (Dialogflow)

Casestudies (link)

Set Expectations (link)

Planner (12 Hours)

Random Thoughts:

🦋 Dialogflow Messenger (Beta Version) for viewing Rich Messages

There are three use cases,

1. Book Store Bot (Papyrus Book House)
2. Coffee Shop Bot (Workflow — link)
3. Weather Bot (+ COVID 19 Bot)

Day 1:

Introducing Chatbots in Dialogflow

Why we need Chatbots?

To work 24 x 7

Works damn well during Pandemics aka BCP

Prerequisites and Software

1. Open an Account with Dialogflow/ Google Cloud

Introducing Dialogflow

Conversation Flow

Setting up Dialogflow

Building Blocks of Chatbots

Agents

Create and manage intents

Agent Settings Versions and environment

Pre-built agents (Coffe Shop/ Tips Calculator)

Small Talk

Multilingual Agents

Introduction to Intents

Intents Create and manage intents

Take example from Coffee Bot

Welcome Intent (When you say, Hello - What should come next)

Fallback Intent (When you don't understand the question, what should be the safer answer)

Training phrases

The more the training phrases, the better the results

Actions and parameters

Responses

Default intents

Rich messages

Introduction to Entities

Entities

Create and manage entities

System entities

Most of these guys will be detected automatically, once we update the Training phrases

Developer entities

Entities designed by Developers

Session entities

Regex entities

Fuzzy matching

Banana Shake/Mango Shake

If you give Apple Shake — It will be considered as a Shake

Contexts

What is Contexts?

Input and output contexts

Lifespan

Each active context has a lifespan that defines the number of conversational turns for which the context remains active. The default lifespan is five conversational turns for normal intents and two conversational turns for follow-up intents. You can override the default lifespan for any contexts. In addition, all contexts expire after 20 minutes of becoming active. When an intent is matched with an output context that is already active, the lifespan and expiration timer are reset.

(Source: Google Documentation)

Follow-up intents

This is quite obvious

Contexts and fulfillment

Knowledgbase

How to uploard Knowledge doc (link)

link for reference document (here)

Book Store (link)

Fulfillment

How fulfillment works?

Configure fulfillment

Webhook for slot filling

Using external API for fulfillment

Day 2: Deploying your chatbot on web Building a webhook endpoint Setting up the webhook endpoint for dynamic data retrieval Configuring Intents with Fulfillment Fulfillment Using Cloud Functions for Firebase Fulfillment Using AWS Lambdas Integrating with Third-party Applications Setting up Facebook App Integration with Facebook messenger Setting up a Slack Workspace Integrating Dialogflow with Slack Quick Introduction to NLP for chatbots Introduction to NLP What is spaCy? POS Tagging Stemming and Lemmatization Named-Entity Recognition Stop-words Dependency Parsing Noun Chunks Finding Similarity

Hello Bots !

lab Setup

Install Python (latest version 3.8.0 +) (link)

Install Anaconda (latest version) (link)

Python libraries to be installed (after Python instalation): NLTK, TextBlob and Spacy (This can be done during the Training session)

import NLTK
import TextBlob 
import Spacy

Register an Account with Dialogflow, Chatfuel, PandoraBots and Wolfram Cloud