Pinned Loading

1. RAG-Notebook RAG-Notebook Public

   Built a custom Retrieval-Augmented Generation (RAG) pipeline for semantic search and question-answering from PDFs, leveraging text chunking and optimized LLM inference with quantization.

   Jupyter Notebook

2. Medical-chatbot-LLM Medical-chatbot-LLM Public

   Implemented a medical PDF chatbot Flask web application using the LLaMA 2 model. The process included preprocessing a medical book PDF file by extracting content, chunking data, and creating embedd…

   CSS

3. RAG-Chunking-Techniques RAG-Chunking-Techniques Public

   In this project, we demonstrate three semantic chunking techniques: Statistical Chunking, Consecutive Chunking, and Cumulative Chunking.

   Jupyter Notebook

4. Hybrid-Retrieval-FAISS-BM25 Hybrid-Retrieval-FAISS-BM25 Public

   Jupyter Notebook

5. K-Means- K-Means- Public

   Jupyter Notebook

6. Classifications-LightGBM-and-CatBoost Classifications-LightGBM-and-CatBoost Public

   Jupyter Notebook