The proposed women’s chatbot (Lucy AI) is designed to address the challenge of understanding complex medical terms, particularly for women’s health queries. Trained on medical datasets including WebMD and eHealthQA, Lucy AI utilizes BERT for fine-tuning to provide responses tailored to women-related medical queries. The chatbot’s primary function is to translate medical jargon into layman language, thereby enhancing accessibility to healthcare information. The chatbot leverages GPT-2 to generate responses based on dataset analysis and references, ensuring contextual relevance. Methodologically, the paper details data preprocessing to ensure accuracy and readiness of models. Evaluation metrics such as BLEU and METEOR scores assess language quality, while performance metrics (96.2% accuracy) evaluate diabetic retinopathy classification using CNN and SVM models. Results demonstrate Lucy AI's efficacy in delivering accurate medical information and classifying diabetic retinopathy stages. Comparative analyses highlight its superiority in healthcare accessibility and personalized medical support. Furthermore, Lucy AI offers features such as a period tracker, mood tracker, and emotional support. The emotional support module utilizes the dataset to provide empathetic responses and assistance. For medical jargon translation, a feed-forward neural network trained on labeled datasets is employed. This comprehensive approach aims to empower women with accessible and personalized healthcare information through innovative technology. Additionally, Lucy AI involves a feature for diabetic retinopathy detection, diabetes-retinopathy is an eye disease that affects the retina. This part of the bot works with the optimized CNN classification of the retinal images into four stages of diabetic retinopathy which is Stage 1: Mild, Stage 2: Moderate, Stage 3: Severe, and Stage 4: Proliferative diabetic retinopathy. In the future expand the horizons of Lucy AI by incorporating more disease detection modules.