chore(similarity): Make message column nullable in grouping records (#…

…1182)

Make message column nullable in grouping records

src/migrations/versions/09b3ef05f1fe_migration.py

@@ -0,0 +1,31 @@
+"""Migration
+
+Revision ID: 09b3ef05f1fe
+Revises: da0a9c9f1bb4
+Create Date: 2024-09-17 17:13:49.660584
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "09b3ef05f1fe"
+down_revision = "da0a9c9f1bb4"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("grouping_records", schema=None) as batch_op:
+        batch_op.alter_column("message", existing_type=sa.VARCHAR(), nullable=True)
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table("grouping_records", schema=None) as batch_op:
+        batch_op.alter_column("message", existing_type=sa.VARCHAR(), nullable=False)
+
+    # ### end Alembic commands ###

src/seer/db.py

@@ -256,7 +256,7 @@ class DbGroupingRecord(Base):
         server_default=text("nextval('grouping_records_id_seq')"),
     )
     project_id: Mapped[int] = mapped_column(BigInteger, primary_key=True, nullable=False)
-    message: Mapped[str] = mapped_column(String, nullable=False)
+    message: Mapped[Optional[str]] = mapped_column(String, nullable=True)
     error_type: Mapped[str] = mapped_column(String, nullable=True)
     stacktrace_embedding: Mapped[Vector] = mapped_column(Vector(768), nullable=False)
     hash: Mapped[str] = mapped_column(String(32), nullable=False)

src/seer/grouping/grouping.py

@@ -1,4 +1,3 @@
-import difflib
 import gc
 import logging
 from functools import wraps
@@ -367,9 +366,6 @@ def get_nearest_neighbors(self, issue: GroupingRequest) -> SimilarityResponse:
 
         similarity_response = SimilarityResponse(responses=[])
         for record, distance in results:
-            message_similarity_score = difflib.SequenceMatcher(
-                None, issue.message, record.message
-            ).ratio()
             should_group = distance <= issue.threshold
 
             if should_group:
@@ -387,7 +383,7 @@ def get_nearest_neighbors(self, issue: GroupingRequest) -> SimilarityResponse:
                 GroupingResponse(
                     parent_hash=record.hash,
                     stacktrace_distance=distance,
-                    message_distance=1.0 - message_similarity_score,
+                    message_distance=0.0,
                     should_group=should_group,
                 )
             )
@@ -443,13 +439,10 @@ def insert_batch_grouping_records(
 
                     if nearest_neighbor:
                         neighbor, distance = nearest_neighbor[0][0], nearest_neighbor[0][1]
-                        message_similarity_score = difflib.SequenceMatcher(
-                            None, entry.message, neighbor.message
-                        ).ratio()
                         response = GroupingResponse(
                             parent_hash=neighbor.hash,
                             stacktrace_distance=distance,
-                            message_distance=1.0 - message_similarity_score,
+                            message_distance=0.0,
                             should_group=True,
                         )
                         groups_with_neighbor[str(entry.group_id)] = response