Smart support bots¶
This repository contains Telegram and Vkontakte bots that help support small and medium-sized businesses in communicating with customers. They close all the typical questions, but something more difficult – redirect to the operators. To increase the quality of communication bots are trained by Dialogflow.
Dialogflow (formerly Api.ai, Speaktoit) is a Google-owned developer of human–computer interaction technologies based on natural language conversations. The company is best known for creating the Assistant (by Speaktoit), a virtual buddy for Android, iOS, and Windows Phone smartphones that performs tasks and answers users’ question in a natural language. Speaktoit has also created a natural language processing engine that incorporates conversation context like dialogue history, location and user preferences. — Wiki.
Telegram bot |
VK bot |
---|---|
View bots in the work can be on the links:
Write in private messages groups Vkontakte.
How to install¶
Copy the scripts to your computer:
git clone https://github.com/eskelevir/support-bots.git
Go to the folder:
cd support-bots
Install the required python packages:
Python3 should be already installed. Then use pip (or pip3, if there is a conflict with Python2) to install dependencies:
pip install -r requirements.txt
Remember, it is recommended to use virtualenv/venv for better isolation.
Get the necessary data to work with Dialogflow (link)
Get the necessary data to work with Vkontakte and Telegram (link)
Create and configure Telegram bot to receive notifications (link)
Training of Dialogflow (link)
Create the file. env and record the received data:
echo "DIALOGFLOW_PROJECT_ID=your project id_of Dialogflow" > .env echo "DIALOGFLOW_LANGUAGE_CODE=language training dialogflow(example 'ru' or 'en')" >> .env echo "GOOGLE_APPLICATION_CREDENTIALS=the path to the json file with the keys to google.cloud" >> .env echo "VK_TOKEN_OF_GROUP=your token of group of Vkontakte" >> .env echo "TG_TOKEN=your token of Telegram" >> .env echo "TG_LOGGER_BOT_CHAT_ID=your chat id of Telegram logger bot" >> .env echo "TG_LOGGER_TOKEN=your token of Telegram logger bot" >> .env Example .env file:
DIALOGFLOW_PROJECT_ID=newagent-hbyugfrt DIALOGFLOW_LANGUAGE_CODE=ru GOOGLE_APPLICATION_CREDENTIALS=credentials.json VK_TOKEN_OF_GROUP=ght5rfyhnee7jgjgd98itkg785hfyr644hfyr7756h TG_TOKEN=125125489:fhHHy4rfg**hjdhry46GGG64gfgrj TG_LOGGER_BOT_CHAT_ID=123456789 TG_LOGGER_TOKEN=25148548:AAGx2C7WH-9gjfurhfytJ0BXeJc6ddjfufurjfmx64hdf-io