Tafsir is a main gateway for a Muslim to study and understand the content of the verses in the Quran. One example is Tafsir Al-Azhar. Tafsir Al-Azhar is a commentary authored by Professor Dr. Hamka, which demonstrates how Dr. Hamka connects modern Islamic history with Quranic studies. Tafsir Al-Azhar has a large number of pages, requiring extra effort when searching for information within it. This research aims to create a system capable of receiving questions about Tafsir Al-Azhar in natural language and answering them in user-friendly terms. The technology used in this research includes Langchain and Large Language Models, implemented using a Telegram chatbot. Telegram was chosen for its popularity and user-friendly interface. The Question Answering system was tested using User Acceptance Testing (UAT) and the DeepEval framework. The UAT resulted in an accuracy score of 83.71%, while testing using the DeepEval framework yielded a hallucination score of 41%, contextual precision of 90%, contextual recall of 81%, and contextual relevancy of 79%.