Navis

Inspiration

What inspired us was our desire to make a change and improve web accessibility. We understand that technology can be daunting, even for the younger generation, and we wanted to create a tool that simplifies navigation and empowers users of all abilities to interact with the digital world more effectively.

What We Learned

Throughout this project, we gained a deeper understanding of integrating AI models, natural language processing, and building a functional bridge between the backend and frontend. Working with advanced technologies like GPT and multimodal AI challenged us to think critically and expand our skills.

How We Built the Project

Our project uses Python as the backend to process user commands and perform actions. We utilized the Flask framework for routing and handling HTTP requests, along with spaCy for natural language processing. For the frontend, we implemented a responsive user interface with JavaScript, HTML, and CSS. Our system processes user voice commands and provides real-time responses, enhancing accessibility.

Key technologies include:

Flask: To handle backend logic and routes.
spaCy: For parsing and understanding natural language commands.
OpenAI GPT: To process complex text-based commands (future potential).
Transformers (Hugging Face): For exploring multimodal AI capabilities like image analysis (future goal).

Challenges We Faced

One of the significant challenges we encountered was utilizing GPT AI and multimodal AI to analyze and perceive images—our initial primary goal. Integrating image processing features with voice commands proved more complex than anticipated due to limited time and resource constraints.

While we couldn’t fully overcome this challenge, we remain confident that with further exploration and refinement, we can achieve this functionality in the future.

Future Vision

Looking ahead, we aim to:

Fully implement multimodal AI features for image analysis and interaction.
Enhance Navis to support users with disabilities, such as those with visual impairments.
Expand Navis to be compatible with a wider range of websites for broader impact.

Conclusion

Though we faced challenges, Navis reflects our commitment to making the web more accessible and intuitive for everyone. We’re excited about the progress we’ve made and the potential for this project to grow into something even more impactful.