Problems.
Write the piece, drive the whole agent loop, or repair a repo by prompting a coding agent. Most are graded against a real model, because that is what you will ship against.
0 of 85 solved
Show me at , . 12 matches
- 04Calculate Embedding SimilarityimplementnumpyL02easy
- 05Build Top-K Semantic SearchimplementnumpyL02easy
- 06Generate Embeddings with Hugging FaceimplementpytorchL02medium
- 07Build a Document ChunkerimplementstdlibL02easy
- 24Measure Retrieval with Recall@k and MRRimplementnumpyL02medium
- 37Rerank the Retrieved Chunksimplement · liveagent · liveL02medium
- 40Build BM25 From ScratchimplementstdlibL02medium
- 47Fuse BM25 and Dense Search With RRFimplementstdlibL02medium
- 72Search by Meaning, Not by Wordsimplement · liveagent · liveL02medium
- 73Rerank With a Model That Understands the Questionimplement · liveagent · liveL02medium
- 75Rewrite the Query Before You Searchimplement · liveagent · liveL02medium
- 76Filter by Metadata Before You Rankimplement · liveagent · liveL02medium
12 of 85 problems