fix: improve OCR indexing and evidence review

backend/migrations/versions/0002_knowledge_index_version.py

@@ -0,0 +1,22 @@
+"""Track the knowledge chunk format so existing documents can be reindexed.
+
+Revision ID: 0002
+Revises: 0001
+"""
+from alembic import op
+import sqlalchemy as sa
+
+revision = "0002"
+down_revision = "0001"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    columns = {column["name"] for column in sa.inspect(op.get_bind()).get_columns("knowledge_documents")}
+    if "index_version" not in columns:
+        op.add_column("knowledge_documents", sa.Column("index_version", sa.Integer(), nullable=False, server_default="1"))
+
+
+def downgrade():
+    op.drop_column("knowledge_documents", "index_version")