Movie recommendation using RASA, TigerGraph

Overview

Demo run:

The below video will highlight the runtime of this setup and some sample real-time conversations using the power of RASA + TigerGraph,

IMAGE ALT TEXT HERE

Steps to run this solution:

Step-0:

Step-1: (Scroll down for detailed setup instructions)

  • cd Movie_Chatbot

Terminal-1:

  • $ rasa train
  • $ rasa run -m models --enable-api --cors "*" --debug

Terminal-2:

  • $ rasa run actions

Step-2: (Scroll down for detailed setup instructions)

  • Run tgcloud solution

Project Overview: Movie recommendations using RASA + TigerGraph

Conversational recommendation systems (CRS) using knowledge graphs is a hot topic as they intend to return the best real-time recommendations to users through a multi-turn interactive conversation. CRS allows users to provide their feedback during the conversation, unlike the traditional recommendation systems. CRS can combine the knowledge of the predefined user profile with the current user requirements to output custom yet most relevant recommendations or suggestions. This work will implement a chatbot using the open-source chatbot development framework - RASA and the most powerful, super-fast, and leading cloud graph database - TigerGraph.

NOTE: This help page will not go into the depth of RASA, TigerGraph functionalities. This help page will touch base and demo how TigerGraph can be integrated with RASA.

Technological Stack

Here is the high-level outline of the technological stack used in this demo project,

Putting things to work

Step-1: (RASA) Implement language models, user intents and backend actions

Beginner tutorial: This is a very good spot to learn about setting up a basic chatbot using RASA and understanding the core framework constructs.

Step-1a: Install RASA

Open a new terminal and setup RASA using the below commands:

  • $ python3 -m virtualenv -p python3 .
  • $ source bin/activate
  • $ pip install rasa

Step-1b: Create new RASA project

  • $ rasa init

After the execution of the above command, a new RASA 'Movie_Chatbot' project will be created in the current directory as shown below,

Below is a kick-off conversation with the newly created chatbot,

Ya, that's quite simple to create a chatbot now with RASA!

Step-1c: Define intents, stories, action triggers

Now, navigate to the project folder Movie_Chatbot/data and modify the default nlu.yml and rules.yml files by adding intents, rules for our movie recommendation business usecase as show below,

Step-1d: Install the TigerGraph python library using pip with the below command,

  • pip install pyTigerGraph

Step-1e: Define action endpoints

Now, navigate to the project folder Movie_Chatbot/actions and modify the actions.py file to include TigerGraph connection parameters and action definitions with the respective movie recommendation CSQL query as show below,

Add the defined action method to the domain.yml as shown below,

Here, 'RecommendMovies' is the name of the CSQL query in the tgcloud database which will discuss in detail in the next section.

With this step, we are done with the installation and configuration of the RASA chatbot.

Step-2: (TigerGraph) Setup TigerGraph database and querying APIs

Beginner tutorial: This is a very good spot to learn about setting up a tigergraph database on the cloud and implementing CSQL queries,

Step-2a: Setup tgcloud database

  • Go to, http://tgcloud.io/ and create a new account.

  • Activate the account.

  • Go to, "My Solutions" and click "Create Solution"

  • Select the starter kit as shown below then click Next twice.

  • Provide a solution name, password tags, and subdomain as needed, and then click 'Next'

  • Enter Submit and close your eyes for the magic!

And Yes!, the TigerGraph Movie recommendation Graph database is created. Buckle up a few more things to do!

  • Go to, GraphStudio and 'Load Data' by selecting the *.csv files and hit the 'play' button as shown below.

  • Once the data is loaded, data statistics should display a green 'FINISHED' message as shown below.

  • Go to, 'Write Queries' and implement the CSQL queries here as shown below,

  • Save the CSQL query and publish it using the 'up arrow' button.

  • Lets, test the query by running with a sample input as shown below,

All Set! The TigerGraph Database is up and running. Are we done? Almost! There is one more thing to do!

Step-2b: Configure secret token

  • Let's set up the secret key access to the cloud TigerGraph API as it is very crucial to ensure a secure way of providing access to the data.

  • Go to, Admin Dashboard->Users->Management and define a secret key as shown below,

  • NOTE: Please remember to copy the key to be used in the RASA connection configuration (Movie_ChatBot/actions/actions.py)

Step-3: (Web UI) Setting up a web ui for the RASA chatbot

  • In this work, we are using an open-source javascript-based chatbot UI to interact with the RASA solution we implemented in Step-1.

  • The RASA server endpoint is configured in the widget/static/Chat.js as shown below,

All right, we are one step close to seeing the working of the TigerGraph and RASA integration.

Step-4: (RASA+TigerGraph) Start RASA and run Actions

Run the below commands in separate terminals,

Terminal-1:

  • $ rasa train
  • $ rasa run -m models --enable-api --cors "*" --debug

Terminal-2:

  • $ rasa run actions

Step-5: (ChatBot UI) Open Chatbot User interface

Hit open widget/index.html to start interacting with the TigerBot movie recommendation engine!

Yes, we are DONE!

I hope this source is informative and helpful.

References:

Owner
Sudha Vijayakumar
Graduate student | Aspiring Software Engineer - Applied Data Science AI/ML/DL
Sudha Vijayakumar
Schema validation for Xarray objects

xarray-schema Schema validation for Xarray installation This package is in the early stages of development. Install it from source: pip install git+gi

carbonplan 22 Oct 31, 2022
Info for The Great DataTas plot-a-thon

The Great DataTas plot-a-thon Datatas is organising a Data Visualisation competition: The Great DataTas plot-a-thon We will be using Tidy Tuesday data

2 Nov 21, 2021
Tandem Mass Spectrum Prediction with Graph Transformers

MassFormer This is the original implementation of MassFormer, a graph transformer for small molecule MS/MS prediction. Check out the preprint on arxiv

Röst Lab 13 Oct 27, 2022
GD-UltraHack - A Mod Menu for Geometry Dash. Specifically a MegahackV5 clone in Python. Only for Windows

GD UltraHack: The Mod Menu that Nobody asked for. This is a mod menu for the gam

zeo 1 Jan 05, 2022
Productivity Tools for Plotly + Pandas

Cufflinks This library binds the power of plotly with the flexibility of pandas for easy plotting. This library is available on https://github.com/san

Jorge Santos 2.7k Dec 30, 2022
Plot, scatter plots and histograms in the terminal using braille dots

Plot, scatter plots and histograms in the terminal using braille dots, with (almost) no dependancies. Plot with color or make complex figures - similar to a very small sibling to matplotlib. Or use t

Tammo Ippen 207 Dec 30, 2022
Matplotlib colormaps from the yt project !

cmyt Matplotlib colormaps from the yt project ! Colormaps overview The following colormaps, as well as their respective reversed (*_r) versions are av

The yt project 5 Sep 16, 2022
Browse Dash docsets inside emacs

Helm Dash What's it This package uses Dash docsets inside emacs to browse documentation. Here's an article explaining the basic usage of it. It doesn'

504 Dec 15, 2022
A curated list of awesome Dash (plotly) resources

Awesome Dash A curated list of awesome Dash (plotly) resources Dash is a productive Python framework for building web applications. Written on top of

Luke Singham 1.7k Jan 07, 2023
A set of useful perceptually uniform colormaps for plotting scientific data

Colorcet: Collection of perceptually uniform colormaps Build Status Coverage Latest dev release Latest release Docs What is it? Colorcet is a collecti

HoloViz 590 Dec 31, 2022
Generate visualizations of GitHub user and repository statistics using GitHub Actions.

GitHub Stats Visualization Generate visualizations of GitHub user and repository statistics using GitHub Actions. This project is currently a work-in-

Aditya Thakekar 1 Jan 11, 2022
A python script editor for napari based on PyQode.

napari-script-editor A python script editor for napari based on PyQode. This napari plugin was generated with Cookiecutter using with @napari's cookie

Robert Haase 9 Sep 20, 2022
Create a visualization for Trump's Tweeted Words Using Python

Data Trump's Tweeted Words This plot illustrates twitter word occurences. We already did the coding I needed for this plot, so I was very inspired to

7 Mar 27, 2022
An interactive dashboard built with python that enables you to visualise how rent prices differ across Sweden.

sweden-rent-dashboard An interactive dashboard built with python that enables you to visualise how rent prices differ across Sweden. The dashboard/web

Rory Crean 5 Dec 19, 2021
This Crash Course will cover all you need to know to start using Plotly in your projects.

Plotly Crash Course This course was designed to help you get started using Plotly. If you ever felt like your data visualization skills could use an u

Fábio Neves 2 Aug 21, 2022
Visualize the bitcoin blockchain from your local node

Project Overview A new feature in Bitcoin Core 0.20 allows users to dump the state of the blockchain (the UTXO set) using the command dumptxoutset. I'

18 Sep 11, 2022
Visualization of numerical optimization algorithms

Visualization of numerical optimization algorithms

Zhengxia Zou 46 Dec 01, 2022
Comparing USD and GBP Exchange Rates

Currency Data Visualization Comparing USD and GBP Exchange Rates This is a bar graph comparing GBP and USD exchange rates. I chose blue for the UK bec

5 Oct 28, 2021
Generate visualizations of GitHub user and repository statistics using GitHub Actions.

GitHub Stats Visualization Generate visualizations of GitHub user and repository statistics using GitHub Actions. This project is currently a work-in-

JoelImgu 3 Dec 14, 2022
Sprint planner considering JIRA issues and google calendar meetings schedule.

Sprint planner Sprint planner is a Python script for planning your Jira tasks based on your calendar availability. Installation Use the package manage

Apptension 2 Dec 05, 2021