feat: chunked bge embeddings + lancedb sutta index

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_index.py

@@ -0,0 +1,14 @@
+from buddhagpt.index import chunk_text
+
+
+def test_chunk_text_respects_max_words():
+    text = " ".join(f"w{i}" for i in range(700))
+    chunks = chunk_text(text, max_words=300, overlap=50)
+    assert all(len(c.split()) <= 300 for c in chunks)
+    assert len(chunks) == 3
+
+
+def test_chunks_overlap():
+    text = " ".join(f"w{i}" for i in range(400))
+    a, b = chunk_text(text, max_words=300, overlap=50)
+    assert a.split()[-50:] == b.split()[:50]