All Projects → karanchahal → Chatagram

karanchahal / Chatagram

Licence: other
Winning ChatBot in the IBM ChatBot competition. A ChatBot for a bank

Programming Languages

python
139335 projects - #7 most used programming language
javascript
184084 projects - #8 most used programming language

Projects that are alternatives of or similar to Chatagram

Botonic
Build chatbots and conversational experiences using React
Stars: ✭ 144 (+1007.69%)
Mutual labels:  watson, chatbots
benchmark-nlp
NLP benchmark test sentences and full results
Stars: ✭ 13 (+0%)
Mutual labels:  watson
Chatbot Watson Android
An Android ChatBot powered by Watson Services - Assistant, Speech-to-Text and Text-to-Speech on IBM Cloud.
Stars: ✭ 169 (+1200%)
Mutual labels:  watson
WatsonCluster
A simple C# class using Watson TCP to enable a one-to-one high availability cluster.
Stars: ✭ 18 (+38.46%)
Mutual labels:  watson
botkit-discord
🤖👾 A Botkit connector for Discord with support for text, voice, attachments, embedded messages, and more.
Stars: ✭ 37 (+184.62%)
Mutual labels:  chatbots
rasa-docker-arm
Rasa Docker image for ARMv7. Runs on a Raspberry Pi.
Stars: ✭ 19 (+46.15%)
Mutual labels:  chatbots
Watsonwebserver
Watson is the fastest, easiest way to build scalable RESTful web servers and services in C#.
Stars: ✭ 125 (+861.54%)
Mutual labels:  watson
watson-document-classifier
Augment IBM Watson Natural Language Understanding APIs with a configurable mechanism for text classification, uses Watson Studio.
Stars: ✭ 41 (+215.38%)
Mutual labels:  watson
rivescript-go
A RiveScript interpreter for Go. RiveScript is a scripting language for chatterbots.
Stars: ✭ 56 (+330.77%)
Mutual labels:  chatbots
Movie-Recommendation-Chatbot
Movie Recommendation Chatbot provides information about a movie like plot, genre, revenue, budget, imdb rating, imdb links, etc. The model was trained with Kaggle’s movies metadata dataset. To give a recommendation of similar movies, Cosine Similarity and TFID vectorizer were used. Slack API was used to provide a Front End for the chatbot. IBM W…
Stars: ✭ 33 (+153.85%)
Mutual labels:  watson
botnaut
Chatbot Framework for Facebook Messenger platform
Stars: ✭ 13 (+0%)
Mutual labels:  chatbots
watson-discovery-food-reviews
Combine Watson Knowledge Studio and Watson Discovery to discover customer sentiment from product reviews
Stars: ✭ 36 (+176.92%)
Mutual labels:  watson
cogy
Cog commands from your Rails app
Stars: ✭ 20 (+53.85%)
Mutual labels:  chatbots
core
The conversational engine and framework that powers the OpenDialog Conversational Experience platform.
Stars: ✭ 32 (+146.15%)
Mutual labels:  chatbots
telegram-bot-sdk
🤖 Telegram Bot API PHP SDK. Create Telegram Bots with PHP Easily! [WIP - DO NOT USE IN PRODUCTION YET]
Stars: ✭ 64 (+392.31%)
Mutual labels:  chatbots
Chat-Bot-Security-Checklist
Chat Bot Security Checklist
Stars: ✭ 20 (+53.85%)
Mutual labels:  chatbots
predict-wildfire-intensity
WARNING: This repository is no longer maintained ⚠️ This repository will not be updated.
Stars: ✭ 32 (+146.15%)
Mutual labels:  watson
Kommunicate-Web-SDK
Kommunicate Web AI Chatbot and Live Chat Plugin
Stars: ✭ 21 (+61.54%)
Mutual labels:  chatbots
neocortex
🧠Neocortex is a tool to connect your cognitive service (e.g. DialogFlow) 🤖 with your communication channels (like facebook) 📞to create amazing bots
Stars: ✭ 24 (+84.62%)
Mutual labels:  chatbots
Wisty.js
🧚‍♀️ Chatbot library turning conversations into actions, locally, in the browser.
Stars: ✭ 24 (+84.62%)
Mutual labels:  chatbots

Chatagram

To install kairos for face recognition

  • in terminal,cd into the directory and type chmod u+x kairos_install.sh and press enter
  • then, type ./kairos_install.sh and press enter
  • kairos would have installed from source

Other dependencies for second server

  • flask (pip install flask)
  • Python 2.7

To start second server

start the server by typing python server2.py in terminal

Screencast Demo

alt text A ChatBot for a bank. Has the following functionalities.

  • Balance check
  • User login
  • Nearest ATM'S plotted on a map
  • Account statement through email
  • Mobile Recharge
  • Funds Tranfer
  • Fixed Deposit Account Opener
  • Calculators for Fixed Deposit, Compound Interest and EMI
  • A feedback system that upsells products at positive sentiment and apologises for negative sentiment and transfers the conversation to a human operator.
  • A speech to text feature for seamless communication

Made using the Watson Conversation API.

How To Build

Requirements are as follows:

  • Python 3.5
  • flask
  • flask_socketio
  • watson_developer_cloud
  • requests
  • fileinput (included with python3.5)
  • json (included with python3.5)
  • urllib (included with python3.5)
  • PIL (in case using windows use 'image')
  • numpy

All these libraries can be installed using the simple pip install <library-name> command. Be sure you are using the pip for python 3.5 and not python 2.7. Use pip3 if you are on Ubuntu.

Use Ubuntu preferably.

How to Run

After installing all these dependencies. Navigate to the repo folder through the terminal. python3 server.py to start the server. This will run on port 3110 on localhost.

Now you have to start the client framework made in react, that is ,in the Chatagram-client repository.

Head over there to complete the building process.

Users and Account information

There is a file named users.json. The chatbot uses this file as the bank's database and looks up the various details like account number, pincode etc .

When testing out the bot, please refer to the the details in this file for logging in etc and email. One can change the email and/or other parameters to test out the email service for account statement.

To access most of the features one would need to log in. To do that you need to enter account number and pin code.

This is done to prove that that the chatbot was constructed in such a way that the bank's operations can be easily plugged in with the use of API's with no substantial code change.

Contact

Don't hesitate to ask for help to run the software. Contact at [email protected]

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].