Thanks a lot for the suggestion! it was indeed much simpler to just modify the JSON Employee Vector Search and the other vector index Results

I implemented a solution that builds upon your approach while adding some additional robustness to handle different types of empty values in my Neo4j vector search results.

def filter_empty_connections(results):
"""
Filter out empty connections from vector search results across all data types
(Employee, Work, Project, WorkAllocation, WorkScheduleRule).
"""
if not results or "results" not in results:
    return results

def is_empty_value(val):
    """Check if a value is considered empty."""
    if isinstance(val, list):
        # Check if list is empty or contains only empty/null values
        return len(val) == 0 or all(is_empty_value(item) for item in val)
    if isinstance(val, dict):
        # Check if dict is empty or contains only empty/null values
        return len(val) == 0 or all(is_empty_value(v) for v in val.values())
    return val is None or val == ""

def filter_single_item(item):
    """Filter empty connections from a single item's connections array."""
    if "connections" not in item:
        return item
        
    filtered_connections = []
    for conn in item["connections"]:
        # Skip the connection if all its non-type fields are empty
        has_non_empty_value = False
        for key, val in conn.items():
            if key != "type" and not is_empty_value(val):
                has_non_empty_value = True
                break
        
        if has_non_empty_value:
            filtered_connections.append(conn)
    
    item["connections"] = filtered_connections
    return item

filtered_items = [
    filter_single_item(item) 
    for item in results["results"]
]

return {"results": filtered_items}

Then I integrated it into my index functions like this:

def employee_details_index(query, query_embedding, n_results=50):
# ... existing query execution code ...

structured_results = []
for row in results:
    employee_data = {
        "employeeName": row["employeeName"],
        "score": row["score"],
        "employee": json.loads(row["employeeJson"]),
        "connections": json.loads(row["connectionsJson"])
    }
    structured_results.append(employee_data)

# Apply filtering before returning
filtered_results = filter_empty_connections({"results": structured_results})
return filtered_results

This approach successfully removed empty connections like "education": [] and "has_unavailability": [] from the results while keeping the connection entries that had actual data.

Thank you again for pointing me in the right direction! This solution worked perfectly for my use case.