GithubHelp home page GithubHelp logo

ricardoribeirorodrigues / ai-chatbot Goto Github PK

View Code? Open in Web Editor NEW
0.0 3.0 0.0 613 KB

ChatBot for discord with Natural Language Processing and Crypto Data Features.

License: MIT License

Python 18.73% PureBasic 11.84% Jupyter Notebook 69.22% Dockerfile 0.21%
chatbot natural-language-processing python webscraping gen-ai

ai-chatbot's Introduction

Discord ChatBot with Natural Language Processing and Crypto Data Features

This project creates a chatbot for Discord with multiple advanced features, integrating real-time cryptocurrency data and various Natural Language Processing (NLP) capabilities.

Features

  1. Crypto Information Retrieval:

    • !run command to provide users with real-time and historical cryptocurrency data.
  2. Web Crawling and Search:

    • Implementation of web crawling capabilities to build a comprehensive database for information retrieval.
  3. Content Filtering:

    • Development of a filtering mechanism to exclude negative content from the downloaded web pages using a trained Neural Network negativity classifier.
  4. Content Generation:

    • Implementation of a neural network trained on the crawled data to generate content (GenAI).
  5. Advanced Content Generation:

    • Enhanced content generation utilizing GPT-2 via HuggingFace transformers.

DevLogs - Short texts explaining the development process for each of the feature iterations of the chatbot.

  • DevLog 0 - Starting the bot structure!
  • DevLog 1 - Adding the !run command to send crypto information to the user.
  • DevLog 2 - Adding web crawling and search functions to the formed database.
  • DevLog 3 - Filter by negativity on the content of downloaded pages.
  • DevLog 4 - Content generation from the crawled database.
  • DevLog 5 - Content generation with GPT (Gpt-2 using HuggingFace transformers)

How to Run Locally

  1. Clone the repository:

    git clone https://github.com/RicardoRibeiroRodrigues/NLP-DiscordBot
  2. Install the dependencies:

    pip install -r requirements.txt
  3. Add the bot's token and the CoinCap API token to a .env file in the following format:

    export TOKEN=bot_token_here
    export API_KEY=api_key_here
  4. Run the setup script (this script will download WordNet):

    python3 manager_script.py setup
  5. Run the bot:

    python3 main.py

    PS: The file `manager_script.py` has a cleanup function to clean all generated data in `data/` and `models/`.

Author

ai-chatbot's People

Contributors

ricardoribeirorodrigues avatar dependabot[bot] avatar

Watchers

Kostas Georgiou avatar  avatar  avatar

ai-chatbot's Issues

Usabilidade

O bot está funcionando, mas poderia ser um pouco melhor no que diz respeito a usabilidade, por exemplo:

  • !help -> retornar um exemplo de uso do !run sem que o usuário tenha que digitar !help run
  • !run -> torná-lo case insensitive ou mesmo fornecer uma lista dos símbolos disponíveis.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.