Recommendation systems provide personalized recommendations to users by analyzing their preferences, behaviors, and other relevant data. They have a vital function in assisting users in navigating the extensive array of accessible information, improving user satisfaction and involvement by providing personalized recommendations. Large Language Models (LLMs) are sophisticated artificial intelligence models that have been trained on massive textual data. They possess the ability to comprehend and produce language that closely resembles human speech. They demonstrate exceptional proficiency in a tasks such as sentiment analysis, text generation, translation, and summarization. LLMs possess the ability to understand context, produce logical responses, and carry out complex language-based tasks, which makes them very adaptable tools in the field of artificial intelligence. LLMs can enhance the quality of recommendations in recommendation systems by comprehending item features. They have the ability to analyze reviews of items, create personalized descriptions of stuff, and offer information on the features of items. The suggested methodology integrates collaborative filtering techniques with LLMs to improve the prediction of recommendations. The results on Amazon dataset with RMSE and MAE evaluation metric shows the efficiency of the proposed model.