From db39a439759a341de39511a3fc3c958131cfa938 Mon Sep 17 00:00:00 2001
From: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Date: Mon, 29 Sep 2025 13:50:11 +0200
Subject: [PATCH] fix: Resolve schema migration for Neo4j (#1482)

<!-- .github/pull_request_template.md -->

## Description
Fix Neo4j issue with migrating DB schema

## Type of Change
<!-- Please check the relevant option -->
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---
 cognee/tasks/schema/ingest_database_schema.py | 12 ++++++------
 cognee/tasks/schema/models.py                 | 11 +++++------
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/cognee/tasks/schema/ingest_database_schema.py b/cognee/tasks/schema/ingest_database_schema.py
index e3823701c..2b1644067 100644
--- a/cognee/tasks/schema/ingest_database_schema.py
+++ b/cognee/tasks/schema/ingest_database_schema.py
@@ -1,3 +1,4 @@
+import json
 from typing import List, Dict
 from uuid import uuid5, NAMESPACE_OID
 from cognee.infrastructure.engine.models.DataPoint import DataPoint
@@ -79,10 +80,10 @@ async def ingest_database_schema(
             schema_table = SchemaTable(
                 id=uuid5(NAMESPACE_OID, name=f"{table_name}"),
                 name=table_name,
-                columns=details["columns"],
+                columns=json.dumps(details["columns"], default=str),
                 primary_key=details.get("primary_key"),
-                foreign_keys=details.get("foreign_keys", []),
-                sample_rows=rows,
+                foreign_keys=json.dumps(details.get("foreign_keys", []), default=str),
+                sample_rows=json.dumps(rows, default=str),
                 row_count_estimate=row_count_estimate,
                 description=f"Relational database table with '{table_name}' with {len(details['columns'])} columns and approx. {row_count_estimate} rows."
                 f"Here are the columns this table contains: {details['columns']}"
@@ -119,9 +120,8 @@ async def ingest_database_schema(
         id=uuid5(NAMESPACE_OID, name=id_str),
         name=migration_config.migration_db_name,
         database_type=migration_config.migration_db_provider,
-        tables=tables,
-        sample_data=sample_data,
-        extraction_timestamp=datetime.now(timezone.utc),
+        tables=json.dumps(tables, default=str),
+        sample_data=json.dumps(sample_data, default=str),
         description=f"Database schema containing {len(schema_tables)} tables and {len(schema_relationships)} relationships. "
         f"The database type is {migration_config.migration_db_provider}."
         f"The database contains the following tables: {tables}",
diff --git a/cognee/tasks/schema/models.py b/cognee/tasks/schema/models.py
index 4b13f420b..54b217c48 100644
--- a/cognee/tasks/schema/models.py
+++ b/cognee/tasks/schema/models.py
@@ -8,9 +8,8 @@ class DatabaseSchema(DataPoint):
 
     name: str
     database_type: str  # sqlite, postgres, etc.
-    tables: Dict[str, Dict]  # Reuse existing schema format from SqlAlchemyAdapter
-    sample_data: Dict[str, List[Dict]]  # Limited examples per table
-    extraction_timestamp: datetime
+    tables: str  # Reuse existing schema format from SqlAlchemyAdapter
+    sample_data: str  # Limited examples per table
     description: str
     metadata: dict = {"index_fields": ["description", "name"]}
 
@@ -19,10 +18,10 @@ class SchemaTable(DataPoint):
     """Represents an individual table schema with relationships"""
 
     name: str
-    columns: List[Dict]  # Column definitions with types
+    columns: str  # Column definitions with types
     primary_key: Optional[str]
-    foreign_keys: List[Dict]  # Foreign key relationships
-    sample_rows: List[Dict]  # Max 3-5 example rows
+    foreign_keys: str  # Foreign key relationships
+    sample_rows: str  # Max 3-5 example rows
     row_count_estimate: Optional[int]  # Actual table size
     description: str
     metadata: dict = {"index_fields": ["description", "name"]}