TaleTutor

An educational platform revolutionizing learning with AI-driven narratives. Personalized lessons, movie-themed experiences, and fictional examples based on real-world principles make learning engaging

Comment

Inspiration

The inspiration for TaleTutor came from the desire to make learning more engaging and effective for students. We recognized that traditional educational methods often fail to connect topics holistically and relate concepts to real-world scenarios, leading to disinterest and fragmented understanding. Drawing from research on narrative learning and the transformative power of storytelling, we envisioned an AI-driven platform that uses immersive narratives to captivate students' imaginations. TaleTutor strives to bridge the gap between abstract concepts and practical applications, making education both fun and meaningful.

What it does

TaleTutor is a narrative-based learning system that serves three primary purposes:

  1. Facilitating Key Connections: Enabling students to make essential connections between concepts by utilising the power of storytelling.
  2. Relating Material to Real-World Scenarios: Connecting academic content with practical applications fosters context based learning.
  3. Making Learning Enjoyable: Using immersive narratives to make education fun.

Features

  1. Dual Interfaces: Separate interfaces for teachers and students.
  2. Themed Learning: Students can choose their learning theme, such as Harry Potter, with subjects like Physics and Civics.
  3. Interactive Chat System: A character-led interactive chat system that dynamically explains concepts based on student interaction.
  4. Real-World Scenario Teaching: Using fictional characters to teach real-world scenarios through engaging narratives.

How we built it

TaleTutor utilizes a LangChain-supported GPT-3.5 LLM to retrieve PDF content uploaded by teachers, convert it into a vectorstore, and perform RAG operations based on student queries. The system processes RAG output with another GPT-3.5 LLM that acts as a router, deciding whether to proceed with narrative building or knowledge retrieval. The GPT-3.5 LLM then generates narratives using zero-shot prompting. The system also manages off-topic queries by guiding students back on track or notifying teachers for relevant follow-up.

Technologies Used

  1. GPT-3.5 LLM: For generating and routing narratives.
  2. LangChain: For managing RAG operations.
  3. Flask: Python server to interface with LLMs.
  4. Next.js: Frontend framework for the user interface.
  5. Axios: Library for making HTTP requests to the server.

Challenges we ran into

During development, we ran into a multitude of issues in regards to both the backend and frontend of our application. Initially, we started off by trying Llama and we ran into port issues which caused pivot to API models. Additionally, routing all agents via LangChain proved to be more challenging and time consuming than expected. As for the frontend, integrating Flask to Next.js was a big learning curve, having trouble with multiple get and post requests to the server containing all of our backend tools. It was also a learning experience getting familiar with Next.js’s styling documentation so bringing last minute touches to the user interface proved to be very tedious.

Accomplishments that we're proud of

  1. Top 10 at UC Berkeley AI Hackathon: Proud to have been selected and placed in the top 10.
  2. Innovative Approach: Conceptualising and implementing an innovative narrative-based learning system.
  3. Team Collaboration: Building a diverse team and developing a full-stack application in under 24 hours.

What's next for TaleTutor?

We have ambitious plans to grow our mission of educating students through captivating characters and unique settings:

  1. Symbiotic System: Developing narratives dynamically by adapting to the student's challenges, allowing the student to learn from the system while the system learns from the student's interactions.
  2. Interconnected Stories: Creating greater interconnectedness in the stories students see.
  3. Emotion Recognition: Expanding our AI model to recognise and respond to emotional changes in students.
  4. Enhanced Interaction: Integrating student voice input directly into the AI’s voice output for better synergy.
  5. Expanded Theme Library: Introducing more characters and settings to cater to diverse student preferences.

Built With

Share this project:

Updates