Add training workflow, datasets, and runbook

2025-12-23 21:17:22 -08:00
commit 619e87aacc
2140 changed files with 2513895 additions and 0 deletions
--- a/training_data/dataset.stats.json
+++ b/training_data/dataset.stats.json
@@ -0,0 +1,7 @@
+{
+  "docs_used": 7,
+  "chunks_written": 1517,
+  "chunk_chars": 6000,
+  "overlap_chars": 400,
+  "min_chars": 1200
+}