updated for 03/2023

.gitignore

@@ -1 +1,5 @@
 /telegram_bot/
+/rasa_nlu/
+__pycache__
+.vscode/
+logs/

NLU_test/nlu_test.py

@@ -1,10 +1,11 @@
 import random
 import time
+from pathlib import Path
 
 from rasa.nlu.model import Interpreter
 
 def get_model():
-    model = "/home/sabrina/PycharmProjects/storyteller_DS/rasa_folder/models/nlu"
+    model = Path(__file__).absolute().parent.joinpath("../rasa_nlu/models/nlu")
 
     interpreter = Interpreter.load(model)
     return interpreter

README.md

@@ -15,9 +15,55 @@ The system is developed and tested using Python 3.7. Some of the libraries requi
 
 ## How To
 
+#### Installation
+- Create environment with conda/mamba
+
+  ```bash
+  conda create -c conda-forge -n storyteller python=3.7
+  conda activate storyteller
+  ```
+- install the requirements `pip install -r requirements.txt`
+- reinstall setuptools to avoid an error: `pip install -U pip setuptools`
+- set up rasa
+
+```bash
+cd storyteller-dialogue-system
+rasa init --init-dir rasa_nlu
+```
+
+Do not train the default model. Use the specified settings to train the model:
+
+```bash
+rasa train nlu --config rasa_nlu/config.yml --nlu rasa_nlu/data/nlu.md --out rasa_nlu/models
+```
+
+Untar the trained model under the `rasa_nlu/models`
+
+```bash
+cd rasa_nlu/models
+tar xvf <model_date-model_time>.tar.gz
+```
+
+- download NLTK data. Run in python
+
+```python
+import nltk
+nltk.download('stopwords')
+nltk.download('twitter_samples')
+nltk.download('averaged_perceptron_tagger')
+nltk.download('wordnet')
+nltk.download('punkt')
+```
+Move the NLTK data dir under your environment path (optional):
+
+```bash
+mv ~/nltk_data /path/to/env/share/nltk_data
+```
+
 #### Set up the Telegram interface
 - Create a Telegram bot following the steps given by the BotFather bot (you can follow this tutorial: https://core.telegram.org/bots#6-botfather) 
 - Modify the `credentials.py` file with your bot name and bot token
+
 #### Set up your local machine as server
 - Registered to Ngrok from `https://ngrok.com/`
 - Go to https://dashboard.ngrok.com/get-started to download the ngrok client
@@ -26,10 +72,10 @@ The system is developed and tested using Python 3.7. Some of the libraries requi
 - Run `./ngrok http 5130`
 - If you are using the Telegram web interface, replace the `bot.setWebhook("https://******.ngrok.io/chat")` in `bot_telegram.py` with the https url generated by ngrok (leave the suffix `/chat` at the end)
 - If you are using the Alana interface, please follow the Alana instruction on how to send requests to Alana.
+
 #### Set up the application
-- Create a virtual environment with Python 3.7
-- Install the requirements in `requirements.txt`
 - Select which engagement strategy to use: currently the system uses the baseline strategy. To use the Feedback Prompt strategy please comment `line 102` of `bot_telegram.py` and uncomment `line 103` of `bot_telegram.py`
+
 #### Run the application
 - Run `bot_telegram.py` to run the system using the Telegram web interface
 

requirements.txt

@@ -1,6 +1,5 @@
-rasa~=1.10.1
-typing~=3.7.4.1
-requests~=2.7.0
+rasa~=1.10.26
+requests
 setuptools~=47.3.1
 flask~=1.1.2
 flask_restful
@@ -16,4 +15,6 @@ scikit-learn~=0.22.2.post1
 networkx~=2.4
 tensorflow~=2.1.1
 transformers~=2.11.0
-nltk~=3.5
+nltk~=3.5
+protobuf~=3.20.1
+markupsafe~=2.0.1