Implement a Simple RAG Pipeline

MediumPython

Problem

Write simple code for a RAG (retrieval-augmented generation) pipeline.

Asked in the L2 round stage. L2 for GenAI developer.

Implement rag_pipeline(documents, query, top_k). Tokenize text case-insensitively, retrieve documents by counting distinct query-token overlaps, preserve input order for ties, and return the selected documents joined with newline characters as a simple extractive answer. Return an empty string when no document matches.

Constraints

1 <= len(documents) <= 100
1 <= top_k <= len(documents)
Documents and query contain printable text
Matching is case-insensitive and punctuation is ignored

Function Signature

def rag_pipeline(documents, query, top_k):

CodePython 3

You need to log in / sign up to run or submit.Ln 2

Run your code to see test output here.