Conventional keyword search matches user query words to document words using an inverted index data structure for efficient matching and ranking by relevancy.
Vector searches have proven to be useful for handling free-text queries, as opposed to the traditional keyword-based search. However, developing a vector search based on word embeddings from a pre-trained model has limitations when it comes to adapting to custom domains. While keyword search can adapt to new domains they are inherently unsuitable for free-text query. How can we combine both these and implement an hybrid search?
LLMs revolutionize question-and-answer systems with exceptional language understanding and creative writing skills. Lossy compression during training may make retrieving information challenging. Leveraging LLMs’ language expertise transforms building question-and-answer systems into reading comprehension using their ability to comprehend text, forming the basis for RAG systems that shift question answering to efficient knowledge base searches.