- Significantly changed the PDF Processor to use Mistral's OCR model

- ensure very long chunks get split into smaller chunks
- ensure TrackedMistralAIEmbedding is batched if needed to ensure correct execution
- upgraded some of the packages to a higher version

migrations/public/versions/605395afc22f_add_nr_of_pages_to_llm_metrics_in_.py

@@ -0,0 +1,31 @@
+"""Add nr_of_pages to llm_metrics in BusinessEvent
+
+Revision ID: 605395afc22f
+Revises: cfee2c5bcd7a
+Create Date: 2025-04-16 07:25:43.959618
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '605395afc22f'
+down_revision = 'cfee2c5bcd7a'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('business_event_log', schema=None) as batch_op:
+        batch_op.add_column(sa.Column('llm_metrics_nr_of_pages', sa.Integer(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('business_event_log', schema=None) as batch_op:
+        batch_op.drop_column('llm_metrics_nr_of_pages')
+
+    # ### end Alembic commands ###