Hartmut/HartOMat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: rich product metadata extraction from STEP files

Browse Source 
Extract volume, surface area, part count, assembly hierarchy, and
complexity from STEP files via OCC B-rep analysis.

Backend:
- extract_rich_metadata() in step_processor.py: computes per-part volume
  (BRepGProp), surface area, triangle/vertex count, assembly depth,
  instance count, complexity score, largest part identification
- cad_metadata JSONB column on Product model (DB migration)
- Auto-populated during STEP processing (non-fatal, 10s timeout)
- Also stored in cad_files.mesh_attributes["rich_metadata"]
- Batch re-extract endpoint: POST /admin/settings/reextract-rich-metadata

AI Agent:
- search_products returns part_count, volume_cm3, complexity, largest_part
- query_database tool description documents cad_metadata schema

Frontend:
- ProductDetail page: CAD Metadata section with stat cards
  (parts, volume, surface area, complexity, triangles, assembly depth)
- Admin System Tools: "Re-extract Rich Metadata" button for backfill

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hartmut Nörenberg
2026-03-15 18:49:50 +01:00
parent 0ffc86589a
commit cfccdd5397
12 changed files with 645 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/services/chat_service.py
+7 -2
View File
@@ -219,7 +219,7 @@ TOOLS = [
"type": "function",
"function": {
"name": "query_database",
"description": "Execute a read-only SQL SELECT query against the database. Key tables/columns: products(id, name, pim_id, category_key, cad_file_id, is_active, tenant_id), orders(id, order_number, status, tenant_id), order_lines(id, order_id, product_id, render_status, material_override, render_overrides), cad_files(id, mesh_attributes->'dimensions_mm' with {x,y,z} in mm, parsed_objects, processing_status). To get product dimensions: JOIN cad_files cf ON cf.id = p.cad_file_id and use cf.mesh_attributes->'dimensions_mm'. Use :tenant_id parameter for tenant filtering. Category is 'category_key' not 'category'.",
"description": "Execute a read-only SQL SELECT query against the database. Key tables/columns: products(id, name, pim_id, category_key, cad_file_id, is_active, tenant_id, cad_metadata JSONB), orders(id, order_number, status, tenant_id), order_lines(id, order_id, product_id, render_status, material_override, render_overrides), cad_files(id, mesh_attributes->'dimensions_mm' with {x,y,z} in mm, parsed_objects, processing_status). products.cad_metadata JSONB contains: part_count, unique_part_count, instance_count, assembly_depth, total_volume_cm3, total_surface_area_cm2, total_triangle_count, complexity_score, largest_part (name + volume_cm3). To get product dimensions: JOIN cad_files cf ON cf.id = p.cad_file_id and use cf.mesh_attributes->'dimensions_mm'. Use :tenant_id parameter for tenant filtering. Category is 'category_key' not 'category'.",
"parameters": {
"type": "object",
"properties": {
@@ -330,7 +330,12 @@ async def _tool_search_products(db: AsyncSession, tenant_id: str, query: str = "
cf.processing_status,
cf.mesh_attributes->'dimensions_mm'->>'x' AS dim_x_mm,
cf.mesh_attributes->'dimensions_mm'->>'y' AS dim_y_mm,
cf.mesh_attributes->'dimensions_mm'->>'z' AS dim_z_mm
cf.mesh_attributes->'dimensions_mm'->>'z' AS dim_z_mm,
p.cad_metadata->>'part_count' AS part_count,
p.cad_metadata->>'total_volume_cm3' AS volume_cm3,
p.cad_metadata->>'complexity_score' AS complexity,
p.cad_metadata->'largest_part'->>'name' AS largest_part_name,
p.cad_metadata->'largest_part'->>'volume_cm3' AS largest_part_volume
FROM products p
LEFT JOIN cad_files cf ON cf.id = p.cad_file_id
WHERE p.tenant_id = :tenant_id