📄️ 👐 Build the RAG application
Let's create a simple RAG workflow that takes in a user query, retrieves contextually relevant documents from MongoDB Atlas, and passes the query and retrieved context to an LLM to generate an answer to the user question.
📄️ 🦹 Re-rank retrieved results
Re-rankers are specialized models that are trained to calculate the relevance between query-document pairs. Without re-ranking the order of retrieved results is governed by the embedding model, which isn't optimized for relevance and can lead to poor LLM recall in RAG applications.