
Qdrant Hybrid Search for Legal RAG Tested on 2,034 Cases
We ran Qdrant hybrid search (RRF + ColBERT + FormulaQuery) on 2,034 Supreme Court precedents. Top-1 went from 31.8% to 86.4%. Code, data, and the 22-query eval are on GitHub.
16 min read
4 articles on this topic.

We ran Qdrant hybrid search (RRF + ColBERT + FormulaQuery) on 2,034 Supreme Court precedents. Top-1 went from 31.8% to 86.4%. Code, data, and the 22-query eval are on GitHub.

We ran Qdrant 1.19 per-tenant IDF on 457k CQADupStack docs. Top-1 changed on 20% of queries. Labeled nDCG barely moved. Methodology, numbers, and the API.

qql-go is archived. Use the qql CLI from qql-rs for CI, runbooks, and agent-safe Qdrant retrieval. This post is the original design.

Inspect RAG chunk boundaries in the browser. A Rust + WebAssembly splitter workbench for debugging overlap, headings, and embedding-ready chunks.