Today, we dive into Retrieval Augmented Generation. This is a way to augment LLMs with additional data coming from a database. The data is first encoded into vectors, and they are stored in a vector database for fast retrieval. We are going to cover the following points:
Great tutorial. Love it! I have a similar use case for an ecommerce application. I have a database of products about 400K items. Am figuring a way to augment LLM to connect to each of these items, so I can connect the user to the right product list when the user asks: "I am looking for an extra small blue striped shirt under 25 dollars".
Great tutorial. Love it! I have a similar use case for an ecommerce application. I have a database of products about 400K items. Am figuring a way to augment LLM to connect to each of these items, so I can connect the user to the right product list when the user asks: "I am looking for an extra small blue striped shirt under 25 dollars".