This repo is a followup for the Medical QA repo where I shared a custom SentenceTransformers model finetuned on medical texts.
In this repo, I'll walk through the process of developing a RAG (Retrieval Augmented Generation) pipeline leveraging various technologies. My pipeline will utilize a custom Sentence Transformers model for semantic similarity computations, integrate with Gemini LLM for answer generation, and interface with Qdrant as the vector store for efficient retrieval.
See the notebook where I annotated the code with comprehensive explanations. You can run it directly on Colab. Feel free to raise an issue if you would like to ask any questions.