Paths/AI Engineer/RAG / The Vector Store
Blend Dense and Sparse Retrieval
Dense vectors find meaning, keyword search finds exact identifiers. Blend the two and add a reranker on top - then say how much weight each side gets.
Validator
⏱ 0:00
IDLE — checks run live as you type commands; submit when done
01Requirements
live checks- File ~/rag/hybrid-search.yaml exists○
- The config defines a dense and a sparse retriever○
- The config states the weights for each retriever○
- The config enables a reranking step○
02Walkthrough
1 of 3 revealed- 01
Write the hybrid configuration
dense finds meaning, sparse finds the exact token. The weights decide which one leads - 0.7 dense and 0.3 sparse is a common starting point.
echo 'retrievers:\n dense:\n index: docs-embeddings\n top_k: 20\n sparse:\n index: docs-keywords\n top_k: 20\nweights:\n dense: 0.7\n sparse: 0.3\nrerank:\n enabled: true\n model: bge-reranker-large\n top_n: 5' > ~/rag/hybrid-search.yaml - 2 locked · each failed submit reveals one
03Stuck?
0 of 3 revealedTake a hint without losing the lab — each one points at the thing to look at, not at the answer.
04AI Tutor
guides, never solvesTell me what you're stuck on — I'll nudge, not solve. Which requirement are you looking at?
04Notebook
saved locally in this browserlearner@lab — ubuntu:24.04
Session is disposable
↑/↓ recalls commands · Ctrl+Enter submits · type help for the command list