woogi/Conflict_Checker
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

feat: text-only structuring prompt for extraction retry ladder

Browse Source
This commit is contained in:
woogi
2026-08-18 13:15:16 -05:00
parent 570300324f
commit 0d109fb5cd
2 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/prompts.py
+24
View File
@@ -281,6 +281,30 @@ If the sheet has no extractable objects, return an empty objects array.
Optional sheet hint: {sheet_hint}"""
# ---------------------------------------------------------------------------
# Stage 2b - text-only structuring (extraction retry ladder, rung 2)
# ---------------------------------------------------------------------------
TEXT_STRUCTURING_SYSTEM_PROMPT = """You are a construction document structuring engine.
You receive the deterministic text layer extracted from one drawing sheet. It is complete and authoritative.
Your ONLY job is to segment it into structured objects. You are NOT reading an image. You must NOT invent, complete, or correct any text.
Rules:
- Every numbered note, schedule row, callout, tag, legend entry, and title-block field becomes its own object.
- source_text must be copied VERBATIM from the input, character-for-character. Never paraphrase.
- Cover the ENTIRE input. Omitting a note is a failure. When unsure of an object's type, use general_note with confidence low.
- Numbers, model numbers, dimensions, and tags must appear in source_text exactly as in the input.
Respond only with valid JSON."""
TEXT_STRUCTURING_USER_INSTRUCTION = """Segment this sheet's text layer into structured construction objects.
Every note, schedule row, callout, tag, and title-block field in the text layer must become an object - omit nothing.
Respond ONLY with a valid JSON object - no markdown fences:
{ "sheet": { "sheet_number": "string or null", "sheet_title": "string or null", "discipline": "string or null", "drawing_type": "string or null", "level": "string or null", "scale": "string or null" }, "objects": [ { "object_id": "string", "object_type": "room | door | window | wall | finish | ceiling | dimension | grid | callout | keynote | general_note | equipment | plumbing_fixture | mechanical_equipment | electrical_device | lighting_fixture | structural_element | schedule_reference | symbol | abbreviation", "category": "architectural | structural | mechanical | electrical | plumbing | code | general", "tag": "string or null", "name": "string or null", "description": "string or null", "attributes": { "attribute_name": "attribute_value" }, "location_key": { "room_number": "string or null", "grid": "string or null", "detail_reference": "string or null" }, "source_text": "VERBATIM text copied from the input", "graphical_basis": null, "review_uses": [ "schedule_comparison", "cross_discipline_coordination", "code_review", "constructability_review" ], "confidence": "high | medium | low" } ], "unresolved_items": [] }
Optional sheet hint: {sheet_hint}
TEXT LAYER (segment ALL of it):
{text_layer}"""
# ---------------------------------------------------------------------------
# Stage 3a - assertion normalization (WIRED: normalizer.py)
# ---------------------------------------------------------------------------