Skip to content

Towards-GenAI/Antenna

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Antenna - Text & Vision Chat with Gemini Pro

Antenna is a powerful, interactive dashboard that leverages Google's state-of-the-art multimodal large language model, Gemini Pro, to provide advanced AI capabilities. With Antenna, users can seamlessly interact with Gemini Pro through a user-friendly interface, enabling them to generate text, analyze images and videos, and perform complex reasoning tasks across multiple modalities.

Deployment Streamlit App

anteena gif

Features

  • Multimodal Interaction: Engage with Gemini Pro using text, images, and videos, all within a single intuitive dashboard.
  • Advanced Language Understanding: Harness the power of Gemini Pro's advanced natural language processing capabilities for tasks such as text generation, summarization, and question-answering.
  • Cross-modal Reasoning: Utilize Gemini Pro's ability to reason across different modalities, enabling sophisticated analysis and insights.
  • Customizable Prompts: Tailor your interactions with Gemini Pro using customizable prompts to achieve desired outputs.
  • Real-time Results: Experience near-instantaneous responses from Gemini Pro, thanks to its optimized performance and speed.

Join Towards-GenAI

Getting Started

To start using Antenna, follow these steps:

  1. Clone the Antenna repository:    git clone https://github.com/Towards-GenAI/Antenna.git  
  2. Install the required dependencies:    cd Antenna  pip install -r requirements.txt  
  3. Set up your Google Cloud credentials and ensure you have access to the Gemini Pro API.
  4. Run the Antenna dashboard:    python Home.py  
  5. Open your web browser and navigate to http://localhost:8501 to access the Antenna dashboard.

Usage

Once you have the Antenna up and running, you can start interacting with Gemini Pro:

  1. Enter your text queries or upload images/videos in the designated input areas.
  2. Customize the prompts to guide Gemini Pro's output, if desired.
  3. Click the "Generate" button to send your input to Gemini Pro for processing.
  4. View the generated results, which may include text, images, or insights derived from the provided input.
  5. Explore different use cases and experiment with various input combinations to unlock the full potential of Gemini Pro.

Contributing

We welcome contributions to enhance Anteena and expand its capabilities. To contribute, please follow these steps:

  1. Fork the repository.
  2. Create a new branch for your feature or bug fix.
  3. Make your changes and ensure the code passes all tests.
  4. Submit a pull request describing your changes. Please refer to the contribution guidelines for more detailed information.

License

Antenna is released under the MIT License.

Acknowledgements

We would like to express our gratitude to the Google DeepMind team for developing the groundbreaking Gemini Pro model and making it accessible to developers and researchers worldwide.

Contact

For any questions, suggestions, or feedback, please reach out to us at info@tushar-aggarwal.com or open an issue on the GitHub repository.

Let Antenna empower your multimodal AI workflows with the cutting-edge capabilities of Gemini Pro!

Releases

No releases published

Packages

No packages published