Note
For video, please look LOOM. Also, this chatbot gives answers related to pediatrics only. It won't give any other answers
Inspiration
We have made this RAG Chatbot for Satya's sister.
Hi, I’m Satya. I come from a family of doctors, especially pediatricians. This app is a small tribute to all the dedicated pediatricians out there—especially my sister.
What it does
Satya's sister is currently pursuing her Master’s in Pediatrics and handles numerous cases every day. Sometimes, for complex or critical cases, she needs to refer to textbooks for accurate and reliable information.
Instead of spending time searching through Google or flipping through heavy books, this app helps her quickly fetch relevant information directly from the textbook. It’s designed to save time and provide accurate references in moments that matter.
How we built it
We use the following tech stacks. Chunked the embeddings into the pinecone vector database. Used Mistral AI for generating text from the relevant documents.(RAG application)
Challenges we ran into
Connecting the front end and backend was a challenging task for us. Especially when we were using the flask API for the first time.
Accomplishments that we're proud of
We showed the app to Satya's sister, and she was very happy. We are really happy that we contributed to today's challenge and made something productive from it.
What we learned
How to build RAG application using LLMS. We also learned about dockers and how it is used for containerization. We also learned about how we
What's next for Model Mash: LLM Arena_code crafters
We will be using different models and try to increase the relevant pediatrics documents and try to scale the application.
Log in or sign up for Devpost to join the conversation.