LingoMate

What it does

• One key to learning a new language is to consistent interaction with native speakers, and exposure to diverse expressions
• LingoMate offers user-friendly, interactive apps that make language learning simple and engaging.
• Compared to the books, video courses, LingoMate is easy to use, simple, and accessible.

How we built it

• Ollama 3.1 is one of LLMs We have used Grafana for monitor and track RAG performance/response. We have used ElasticSearch for vector database and postgres to save user feedback and conversation histories. We have used streamlit to implement interface with limited resource.

Challenges we ran into

• Optimize prompts to yield appropriate/consistent answers
• Finding/Preparing datasets
• Enhance RAG Tracing
  

Accomplishments that we're proud of

-I was new to AI and I am proud that I could absorb/experience LLM in such short time. -It was good to put myself into a learner's shoes (who I used to be) and explore how we can help language learners.

What's next for LingoMate

• Expand into multiple languages. Offer more combinations of input/output languages to scale it up
• Scale up data sets, cover broader topics, enhance model performance
• Offer features to track histories of conversations for a user.
• Enhance UI
• With data-driven recommendations, we are aiming to let users to personalize their learnings

Built With

• elasticsearch
• llama
• postgresql
• python
• streamlit