updated ocr viewer, built and tested ai workflows and OCR.

Built out use cases

Built out googledocumentOCR and a semantic search webpage

check_db.py

@@ -0,0 +1,24 @@
+import sys
+sys.path.insert(0, 'GoogleDocumentOCR')
+from db import get_conn
+
+conn = get_conn()
+cur  = conn.cursor()
+
+cur.execute("""
+    SELECT nationality, corpus, chunk_type, COUNT(*)
+    FROM document_chunks
+    GROUP BY nationality, corpus, chunk_type
+    ORDER BY nationality, corpus, chunk_type
+""")
+print(f"{'Nationality':<12} {'Corpus':<26} {'Type':<14} {'Count':>6}")
+print("-" * 64)
+for nat, corpus, ctype, count in cur.fetchall():
+    print(f"{nat:<12} {corpus:<26} {ctype:<14} {count:>6}")
+
+cur.execute("SELECT COUNT(*) FROM document_chunks")
+print(f"\nTOTAL: {cur.fetchone()[0]} chunks")
+
+cur.close()
+conn.close()
+