👐 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.

Fill in any <CODE_BLOCK_N> placeholders and run the cells under the Step 8: Build the RAG application section in the notebook to build the RAG "application".

The answers for code blocks in this section are as follows:

CODE_BLOCK_14

Answer

vector_search(user_query)

CODE_BLOCK_15

Answer

create_prompt(user_query)

CODE_BLOCK_16

Answer

[{"role": "user", "content": prompt}]