feat: bilara corpus ingestion to suttas.jsonl

2026-08-14 17:06:26 -07:00
parent 76d1858ffe
commit f456877b58
4 changed files with 52 additions and 0 deletions
--- a/scripts/fetch_corpus.sh
+++ b/scripts/fetch_corpus.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+set -euo pipefail
+mkdir -p corpus/raw
+git clone --depth 1 https://github.com/suttacentral/bilara-data corpus/raw/bilara-data