{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f80a5ec68c234eb18c6753c6987064ac\" frameborder=\"0\" width=\"1152\" height=\"864\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":864,"width":1152,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":864,"thumbnail_width":1152,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f80a5ec68c234eb18c6753c6987064ac-00001.gif","duration":253.86,"title":"Building an E2E RAG Solution with Domain Adapted Language Model (DALM)","description":"In this video, I will explain how to build an end-to-end drag solution using a domain adapter language model. We will cover the steps of installing the necessary dependencies, preparing the training data, and implementing the model. Our model will take user queries, draw from available passages, and generate relevant answers. I will also demonstrate how to generate synthetic training data using GPT-5 and the Hsikas guide dataset. By the end of this video, you will have a clear understanding of how to build and train a drag model for your specific domain."}