Loading repository data…
Loading repository data…
umairqadir97 / repository
POC project done for building a Chat-Bot or Conversational-AI using (Python, Flask, Machine Learning, Rasa NLU, Redis, MySQL)
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
Architeture:
For Roman-Urdu & English, two separate agents are trained, evaluated and tested. Each having its own trainin samples, but same intent_names, actions & domain
Features
There are 3 branches for project right now. 1- Master is holding the code version that is being used in live demo 2- Development other than live demo, latest stable code will be pushed here. 3- Dev2 all the tests can be conducted on this branch. OR incase multiple developers are working on project.
$ sudo apt-get update -y
$ sudo apt-get install docker.io
$ sudo curl -L https://github.com/docker/compose/releases/download/1.21.2/docker-compose-`uname -s`-`uname -m` -o /usr/local/bin/docker-compose
$ sudo chmod +x /usr/local/bin/docker-compose
$ cd base_docker;
$ bash ./base_docker.sh
$ cd ..
$ bash ./run.sh
This installation is only for backend of Chatbot system.
This installation is only for backend of Chatbot system.
Setup Virtual Environment (Linux Environment):
$ virtualenv --python=python3 venv
$ source venv/bin/activate
pip install -r requirements.txt
Your environment should be ready by now :smiley: !
Clone Project & open terminal in chatbot root directory 'tp_chatbot_rasa'
activate virtual environment
source venv/bin/activate
run commands for RASA Action server:
rasa run actions --port 5005
open a new terminal window
activate the virtual environment by 2
run commands for RASA API server
rasa run -m models/ --enable-api --log-file out.log --cors "*" --endpoints endpoints.yml --port 8000 --debug
python3 api.py
Setup and Port Numbers for Multi-Lingual Chatbot Redis Tracker Store: 6379 tracker_store: type: redis url: localhost port: 6379 db: 0 password:
Redis Interface: redis-commander (at port 8081)
Roman Urdu chat agent:
actions server:
>> rasa run actions -p 5056
shell/api server to listen action server:
(define action endpoint in endpoints.yml)
>> rasa shell --endpoints endpoints.yml -p 5006 --debug
English chat agent:
actions server:
>> rasa run actions -p 5055
shell/api server to listen action server:
(define action endpoint in endpoints.yml)
>> rasa shell --endpoints endpoints.yml -p 5005 --debug
>> todo: update docker file for single run, update readme for local UI, dockerized version is a bit slower,
clean readme, add directory structure, test cases for complete chatbot system