Politecnico of Turin Thesis: "Implementation and Evaluation of an Educational Chatbot based on NLP Techniques"

Overview

THESIS_CAIRONE_FIORENTINO

Politecnico of Turin Thesis: "Implementation and Evaluation of an Educational Chatbot based on NLP Techniques"

GENERATE TOKEN SLACK

NB: REMEMBER TO REGENERATE SLACK TOKENS AND CHANNEL ID IF ARE DISABLE (SEE THESIS PDF)

  • Go on your Slack App ( App Slack )-> select your app or create new -> Settings -> Install App -> (regenerate two tokens) -> Copy Tokens in actions/Constants.py and credentials.yml files.

RASA - LOCAL MODE

Components Installation

  • Writing in Anaconda console this command:
    • conda create --name venv python==3.8.0
    • conda activate venv
    • conda install ujson tensorflow
    • pip install rasa
    • pip install rasa[spacy] for SPACY configuration
    • pip install rasa[trasformers] for BERT configuration
    • rasa init if you want to create new project

MORE INFO: See this video: link

Code Execution

  • First, in TESI_POLI_POBOT directory do the training in anaconda console with venv activate:

    • rasa train --config configs/{file_cofiguration}.yml --fixed-model-name {model_name}
  • After run server rasa:

  • rasa run --connector slack --model {model_name} --debug

  • In an other prompr run server rasa ACTIONS:

  • rasa run actions --action actions --debug

  • If you want,to test locally the intent classification, run in Anaconda console:

    • rasa train --config configs/{file_cofiguration}.yml --fixed-model-name {model_name}
    • rasa shell --model {model_name}

Rasa Bot - Slack Connection

  • after training and running the server in Anaconda console (see ## Execution of code paragraph):
    • in BOT_RASA/ngrok directory run this command (in console prompt):
      • ngrok http 5005 to create a tunnel for localhost:5005 address:
      • select the forwarding address choose to ngrok ({address} = http://<number_code>.ngrok.io)
      • in Slack App link save the address (selecting in Features menu):
        • Interactivity & Shortcut > Request URL: ({address}/webhooks/slack/webhook) > Save Changes
        • OAuth & Permissions > Redirect URLs > Add : ({address}/webhooks/slack/webhook) > Save URLs
        • Event Subscriptions > Enable Events (Request URL) > Change: ({address}/webhooks/slack/webhook) > Save Changes
      • expired time of ngrok address: 2 hours. (when we will use a public address, ngrok will become USELESS)
  • tokens bot save as environment variable in PC server (for security issue)
  • Slack bot: link

To Connect also the ACTION Server Rasa:

  • ngrok http 5055 to create a tunnel for localhost:5055
  • In endpoints.yml modify url of action_endpoint: {address}/webhook

RASA X

Components Installation

  • Writing in Anaconda console this command:
    • conda create --name venv python==3.9.0
    • conda activate venv
    • conda install ujson tensorflow
    • pip install rasa[spacy] for SPACY configuration
    • pip install rasa[trasformers] for BERT configuration
    • pip install --upgrade pip==20.0.1 pip3 install rasa-x --extra-index-url https://pypi.rasa.com/simple pip install --upgrade pip

Code Execution

  • First, in TESI_POLI_POBOT directory do the training in anaconda console with venv activate:

    • set PYTHONUTF8=1
    • rasa x --connector slack --config configs/{file_cofiguration}.yml
  • In an other prompt run server rasa ACTIONS:

  • rasa run actions --action actions --debug

Rasa Bot - Slack Connection

  • after training and running the server in Anaconda console (see ## Execution of code paragraph):
    • in BOT_RASA/ngrok directory run this command (in console prompt):
      • ngrok http 5005 to create a tunnel for localhost:5005 address:
      • select the forwarding address choose to ngrok ({address} = http://<number_code>.ngrok.io)
      • in Slack App link save the address (selecting in Features menu):
        • Interactivity & Shortcut > Request URL: ({address}/webhooks/slack/webhook) > Save Changes
        • OAuth & Permissions > Redirect URLs > Add : ({address}/webhooks/slack/webhook) > Save URLs
        • Event Subscriptions > Enable Events (Request URL) > Change: ({address}/webhooks/slack/webhook) > Save Changes
      • expired time of ngrok address: 2 hours. (when we will use a public address, ngrok will become USELESS)
  • tokens bot save as environment variable in PC server (for security issue)
  • Slack bot: link

To Connect also the ACTION Server Rasa:

  • ngrok http 5055 to create a tunnel for localhost:5055
  • In endpoints.yml modify url of action_endpoint: {address}/webhook

To Connect also the ACTION Server Rasa X:

  • ngrok http 5055 to create a tunnel for localhost:5002
  • In credentials.yml modify url of rasa: {address}/api

RASA - DOCKER MODE

Code Execution

If is the first time, run this commands:

docker volume create db-volume
docker-compose up -d
docker-compose down
docker-compose up -d
python rasa_x_commands.py create --update admin me <password_rasa_server> (i.e. password)
docker-compose down
docker-compose up -d

Otherwise, in TESI_POLI_POBOT directory in console run only this command:

  • docker-compose up -d

Rasa Bot - Slack Connection

After all container is in running mode, in web browser go in `http:://localhost:80' and insert the password choose the first time. (i.e. password)

If rasa x server not contain NLU data (possible first time) you can upload the file directly using interface of rasa x server in Training -> NLU data / Stories / Rules / Configuration (copy and paste the content of config choose in TESI_POLI_POBOT directory)

If you want to connect to slack:

  • after training and running the server in Anaconda console (see ## Execution of code paragraph):
    • in BOT_RASA/ngrok directory run this command (in console prompt):
      • ngrok http 80 to create a tunnel for localhost:80 address:
      • select the forwarding address choose to ngrok ({address} = http://<number_code>.ngrok.io)
      • in Slack App link save the address (selecting in Features menu):
        • Interactivity & Shortcut > Request URL: ({address}/core/webhooks/slack/webhook) > Save Changes
        • OAuth & Permissions > Redirect URLs > Add : ({address}/core/webhooks/slack/webhook) > Save URLs
        • Event Subscriptions > Enable Events (Request URL) > Change: ({address}/core/webhooks/slack/webhook) > Save Changes
      • expired time of ngrok address: 2 hours. (when we will use a public address, ngrok will become USELESS)
  • tokens bot save as environment variable in PC server (for security issue)
  • Slack bot: link

RASA - TEST DATA

Test stories in tests directory

  • if you want tests stories with cross-validation:
    • rasa train --config configs/{file_cofiguration}.yml --fixed-model-name {model_name} (if model does not exist)
    • rasa test --config configs/{file_cofiguration}.yml --cross-validation --runs {time_runs} --folds {num_folds} --out {dir_out} --model {model_name}

Test NLU data

  • if you want test only the NLU data splitted:

    • rasa train nlu --nlu train_test_split/training_data.yml --config configs/{file_cofiguration}.yml --fixed-model-name ./models_NLU/{model_name} (if model does not exist)
    • rasa test nlu --nlu train_test_split/test_data.yml --out {dir_out} --model ./models_NLU/{model_name}
  • if you want test only the NLU data totally:

    • rasa train nlu --config configs/{file_cofiguration}.yml --fixed-model-name {model_name} (if model does not exist)
    • rasa test nlu --nlu train_test_split/test_data.yml --out {dir_out} --model {model_name}

Test CORE data

  • if you want test only the CORE data:
    • rasa train --config configs/{file_cofiguration}.yml --fixed-model-name {model_name} (if model does not exist)
    • rasa test core --stories tests/test_stories.yml --out {dir_out} --model {model_name}
Owner
cairone_fiorentino97
cairone_fiorentino97
(CVPR 2022) Pytorch implementation of "Self-supervised transformers for unsupervised object discovery using normalized cut"

(CVPR 2022) TokenCut Pytorch implementation of Tokencut: Self-supervised Transformers for Unsupervised Object Discovery using Normalized Cut Yangtao W

YANGTAO WANG 200 Jan 02, 2023
A Comparative Review of Recent Kinect-Based Action Recognition Algorithms (TIP2020, Matlab codes)

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms This repo contains: the HDG implementation (Matlab codes) for 'Analysis and

Lei Wang 5 Oct 22, 2022
Safe Bayesian Optimization

SafeOpt - Safe Bayesian Optimization This code implements an adapted version of the safe, Bayesian optimization algorithm, SafeOpt [1], [2]. It also p

Felix Berkenkamp 111 Dec 11, 2022
4st place solution for the PBVS 2022 Multi-modal Aerial View Object Classification Challenge - Track 1 (SAR) at PBVS2022

A Two-Stage Shake-Shake Network for Long-tailed Recognition of SAR Aerial View Objects 4st place solution for the PBVS 2022 Multi-modal Aerial View Ob

LinpengPan 5 Nov 09, 2022
A naive ROS interface for visualDet3D.

YOLO3D ROS Node This repo contains a Monocular 3D detection Ros node. Base on https://github.com/Owen-Liuyuxuan/visualDet3D All parameters are exposed

Yuxuan Liu 19 Oct 08, 2022
Python scripts performing class agnostic object localization using the Object Localization Network model in ONNX.

ONNX Object Localization Network Python scripts performing class agnostic object localization using the Object Localization Network model in ONNX. Ori

Ibai Gorordo 15 Oct 14, 2022
PyTorch code for DriveGAN: Towards a Controllable High-Quality Neural Simulation

PyTorch code for DriveGAN: Towards a Controllable High-Quality Neural Simulation

76 Dec 24, 2022
In-place Parallel Super Scalar Samplesort (IPS⁴o)

In-place Parallel Super Scalar Samplesort (IPS⁴o) This is the implementation of the algorithm IPS⁴o presented in the paper Engineering In-place (Share

82 Dec 22, 2022
Code and Data for the paper: Molecular Contrastive Learning with Chemical Element Knowledge Graph [AAAI 2022]

Knowledge-enhanced Contrastive Learning (KCL) Molecular Contrastive Learning with Chemical Element Knowledge Graph [ AAAI 2022 ]. We construct a Chemi

Fangyin 58 Dec 26, 2022
Pytorch-3dunet - 3D U-Net model for volumetric semantic segmentation written in pytorch

pytorch-3dunet PyTorch implementation 3D U-Net and its variants: Standard 3D U-Net based on 3D U-Net: Learning Dense Volumetric Segmentation from Spar

Adrian Wolny 1.3k Dec 28, 2022
LiDAR R-CNN: An Efficient and Universal 3D Object Detector

LiDAR R-CNN: An Efficient and Universal 3D Object Detector Introduction This is the official code of LiDAR R-CNN: An Efficient and Universal 3D Object

TuSimple 295 Jan 05, 2023
Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

Infinitely Deep Bayesian Neural Networks with SDEs This library contains JAX and Pytorch implementations of neural ODEs and Bayesian layers for stocha

Winnie Xu 95 Nov 26, 2021
Progressive Coordinate Transforms for Monocular 3D Object Detection

Progressive Coordinate Transforms for Monocular 3D Object Detection This repository is the official implementation of PCT. Introduction In this paper,

58 Nov 06, 2022
Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.

Learning Associative Inference Using Fast Weight Memory This repository contains the offical code for the paper Learning Associative Inference Using F

Imanol Schlag 18 Oct 12, 2022
Styleformer - Official Pytorch Implementation

Styleformer -- Official PyTorch implementation Styleformer: Transformer based Generative Adversarial Networks with Style Vector(https://arxiv.org/abs/

Jeeseung Park 159 Dec 12, 2022
Library for 8-bit optimizers and quantization routines.

bitsandbytes Bitsandbytes is a lightweight wrapper around CUDA custom functions, in particular 8-bit optimizers and quantization functions. Paper -- V

Facebook Research 687 Jan 04, 2023
A Re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"

What is This This is a simple re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"(1). Only Sections

102 Dec 14, 2022
PyTorch implementation of HDN(Homography Decomposition Networks) for planar object tracking

Homography Decomposition Networks for Planar Object Tracking This project is the offical PyTorch implementation of HDN(Homography Decomposition Networ

CaptainHook 48 Dec 15, 2022
An open source Python package for plasma science that is under development

PlasmaPy PlasmaPy is an open source, community-developed Python 3.7+ package for plasma science. PlasmaPy intends to be for plasma science what Astrop

PlasmaPy 444 Jan 07, 2023
ReGAN: Sequence GAN using RE[INFORCE|LAX|BAR] based PG estimators

Sequence Generation with GANs trained by Gradient Estimation Requirements: PyTorch v0.3 Python 3.6 CUDA 9.1 (For GPU) Origin The idea is from paper Se

40 Nov 03, 2022