This project uses a hybrid artificial intelligence framework that combines the Vision Language Model - ALBEF (Align Before Fuse) with the Retrieval-Augmented Generation (RAG) framework to automatically generate medical reports from Chest X-ray images. Initially trained on the Indiana University Open-i dataset, ALBEF retrieves relevant medical reports as contextual references. These reports are then used as prompts in the RAG framework, which works with the open-source generative model Mistral AI open-mistral-7b, to create detailed and accurate radiological findings. This approach generates reports that are coherent with a radiologist’s written report and can also be tailored to specific clinical settings through prompt engineering. The goal is to enhance report accuracy and reduce the time healthcare professionals spend on the time- consuming task of report generation.