Building RAG: All things retrieval

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?

March 2, 2024 ยท Sai