A Discord bot using the power of Google's Gemini-Pro API to interact with users in both text and image formats. It processes messages and images sent to it, generating creative and engaging responses.
Gemini API is completely free for upto 60 calls/min as of Jan 2024.
- AI-Geneated Text Responses: ThunderAI creates text responses using Google's Gemini AI.
- Image Processing: ThunderAI responds to images, combining text and visual inputs for engaging interactions (Images should be under 2.5 Megs).
- Message History Management: Each channel/thread has its own context, manageable with
/forget. Note that, due to API restrictions, the bot cannot remember image interactions. - Customizable Language Response: This bot consistently generates responses in English, regardless of the language in which the user sends messages. However, you have the flexibility to customize it to respond in any other language of your choice.
- Bot Knowledge: Elevate your interactions by imbuing ThunderAI with personalized prompts and insights. The bot retains this knowledge, allowing it to craft engaging responses tailored to your specific contributions.
You need Google API Key for it. SO, Get a Google Gemini Api Key from https://makersuite.google.com/app
You need Discord Bot Token. So, Make a Discord Bot from https://discord.com/developers/applications
- Locate to
config.pyfile and Fill the following values:
GEMINI_API_KEY- Your Gemini API Key (https://makersuite.google.com/app)DISCORD_BOT_TOKEN- Your Discord Bot Token (https://discord.com/developers/applications)CHANNEL_ID- Put ID of the channel where you want ThunderAI to Interact!
-
Install all dependencies as specified in
requirements.txt -
Run
main.py
- The bot's behavior is subject to the limitations and rules of the Discord API and the Gemini API.
- The bot's responses are generated by the Gemini API and are not controlled by the developer.
Contributions are welcome! Please feel free to submit a pull request.
This project is licensed under the terms of the MIT license.