HarlanBOT

HarlanBOT is a Python module designed for creating AI-based chatbots. This module utilizes various natural language processing (NLP) and deep learning technologies to enable the bot to learn from registered conversation samples and provide relevant responses based on user input.

Features

• Easy Customization: Easily add, modify, or remove intents and responses in the JSON file.
• Train the ChatBot: Train the chatbot using data from a JSON file containing intents and responses.
• Real-time Interaction: The chatbot can respond in real-time based on user input.

Installation

Follow the steps below to install and set up HarlanBOT:

Installation Steps

1. Install the package:

   pip install harlanbot
   

   This requires the modified tflearn package for compatibility with the AI:

   pip install git+https://github.com/harlansr/tflearn.git@master
   

2. Create a Python script:

   from harlanbot import ChatBot
   bot = ChatBot()
   

   Run this code for the first time to create the files/intents.json file. You can also customize the file name as needed by passing a custom path.

   from harlanbot import ChatBot
   bot = ChatBot(files="custom_file_name")
   

   This example will create a file named custom_file_name/intents.json.

3. Edit the intents.json file:

   intents.json is the file required to train the bot. To tailor the chatbot to your needs, edit the contents of the intents.json file.

Usage

Example intents.json File

{
    "intents": {
        "main": [
            {
                "tag": "greeting",
                "patterns": [
                    "hello",
                    "who are you"
                ],
                "responses": [
                    "Hello, I'm your assistant",
                    "Hi, I'm your assistant"
                ]
            },
            {
                "tag": "goodbye",
                "patterns": [
                    "bye",
                    "I need to go"
                ],
                "responses": [
                    "Okay, have a nice day",
                    "See you again"
                ]
            }
        ]
    }
}

Explanation:

Training the ChatBot

After customizing the intents.json file, when you run:

bot.train()

This will train the AI according to the data in intents.json. Alternatively, you can train the model everytime code running by modify the code like this:

from harlanbot import ChatBot
bot = ChatBot(train=True)

Documentation

Functions

Class ChatBot( train, accuracy, files, message_default )

Function ask( message, need_accuracy )

Function run_loop( need_accuracy )

Example Code

from harlanbot import ChatBot

bot = ChatBot(True, 0.9)  # Set to False if you don't want the bot to train every time
answer = bot.ask("Hello, nice to meet you") 
print(answer)

Contributing

If you'd like to contribute to this project, please follow these steps:

1. Fork the GitHub repository
2. Create a new branch (git checkout -b new-feature)
3. Make the necessary changes
4. Commit the changes (git commit -am 'Add new feature')
5. Push the branch (git push origin new-feature)
6. Create a Pull Request