https://yonk.dev/tags/ai/Recent content in Ai on Yonk-LabsHugo -- gohugo.ioen© 2026 Yonk-LabsThu, 16 Apr 2026 00:00:00 +0000https://yonk.dev/blog/graphrag-part3-scotus-showdown/Thu, 16 Apr 2026 00:00:00 +0000https://yonk.dev/blog/graphrag-part3-scotus-showdown/Part 3 of 3. 391 real SCOTUS cases, four retrieval strategies running side by side, multi-hop Cypher that no hybrid search can match, and the production-ready 3-stage architecture you should actually ship.https://yonk.dev/blog/graphrag-part1-vector-vs-graph/Tue, 14 Apr 2026 00:00:00 +0000https://yonk.dev/blog/graphrag-part1-vector-vs-graph/Part 1 of 3. Users ask three shapes of questions and only one of them needs a graph. Honest benchmarks, a 3-stage retrieval architecture, and why graph is a multiplier — not a replacement.https://yonk.dev/blog/training-sets-for-lora-nl2sql/Mon, 13 Apr 2026 00:00:00 +0000https://yonk.dev/blog/training-sets-for-lora-nl2sql/A layered training corpus — domain pairs, public ballast, and a reusable Postgres syntax corpus — is 80% of the work for a NL2SQL LoRA. The training config is YAML and patience.https://yonk.dev/blog/building-your-semantic-layer/Sun, 05 Apr 2026 00:00:00 +0000https://yonk.dev/blog/building-your-semantic-layer/A step-by-step walkthrough of building a PostgreSQL semantic layer in pg_agents — crawl the schema, enrich it, define your vocabulary, lock down categoricals, and promote the queries that work.https://yonk.dev/blog/why-llms-fail-at-nl2sql/Fri, 03 Apr 2026 00:00:00 +0000https://yonk.dev/blog/why-llms-fail-at-nl2sql/Raw LLMs hit 10-20% accuracy on real enterprise schemas with cryptic column names and tribal-knowledge joins. Here’s why, and the semantic-layer fix that takes you from toy to production.