File size: 3,887 Bytes
1b4b6d2 8682034 1b4b6d2 8a25d8e 1b4b6d2 1997b5a 1b4b6d2 c1e71b3 8a25d8e c1e71b3 0d71027 c1e71b3 0d71027 c1e71b3 0d71027 c1e71b3 1b4b6d2 b9ca909 1b4b6d2 b9ca909 1b4b6d2 0d71027 1b4b6d2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | """
STEP 2 — Classify Pages
AI reads each page title/text and assigns drawing type
User can correct any misclassification
"""
import pandas as pd
import os, io, re, json
from pdf_engine.smart_classifier import classify_all_pages, PAGE_ITEMS_MAP
from pdf_engine.pdf_loader import page_to_pil
from workflow.workflow_state import mark_step_done
# Candidate types per PDF kind — used by the AI-vision refiner
_STRUCT_TYPES = ["foundations", "tie_beam", "column_layout", "upper_columns", "neck_columns",
"columns_1f", "columns_2f", "columns_roof",
"slab_1st", "slab_2nd", "roof_slab"]
_ARCH_TYPES = ["ground_floor_plan", "first_floor_plan", "second_floor_plan",
"roof_floor_plan", "elevations", "setting_out", "schedules"]
def _ai_classify(img_input, pdf_type: str):
"""Classify ONE page by vision when keyword matching is unsure. Returns a
PAGE_ITEMS_MAP key or None."""
from utils.key_manager import get_key_manager
mgr = get_key_manager()
api_key, current_model = mgr.get_key_and_model()
if not api_key or api_key == "NO_API_KEY_FOUND":
return None
choices = _STRUCT_TYPES if pdf_type == "structural" else _ARCH_TYPES
try:
from google import genai
from google.genai import types
import time
import io as _io
if isinstance(img_input, bytes):
img = img_input
elif isinstance(img_input, str) and os.path.exists(img_input):
with open(img_input, "rb") as f:
img = f.read()
elif isinstance(img_input, np.ndarray):
pil_img = page_to_pil(img_input)
buf = _io.BytesIO()
pil_img.save(buf, format="PNG")
img = buf.getvalue()
else:
return None
prompt = (
f"This is a construction drawing. Classify it as one of: {choices}. "
"Reply ONLY with valid JSON: {\"type\": \"<chosen_type>\"}"
)
for attempt in range(2):
api_key, current_model = mgr.get_key_and_model()
if not api_key or api_key == "NO_API_KEY_FOUND":
return None
try:
client = genai.Client(api_key=api_key, http_options={'timeout': 10})
resp = client.models.generate_content(
model=current_model,
contents=[types.Part.from_bytes(data=img, mime_type="image/png"), prompt])
raw = re.sub(r"```json|```", "", resp.text).strip()
result = json.loads(raw).get("type")
return result if result in PAGE_ITEMS_MAP else None
except Exception as e:
last_err = str(e)
if any(code in last_err for code in ("429", "RESOURCE_EXHAUSTED", "quota")):
mgr.mark_rate_limited(api_key, current_model)
continue
time.sleep(1)
return None
except Exception:
return None
def _classify_single(text: str, pdf_type: str) -> dict:
from pdf_engine.smart_classifier import PAGE_ITEMS_MAP
text_lower = text.lower()
scores = {}
for ptype, config in PAGE_ITEMS_MAP.items():
# Enforce PDF domain isolation (structural vs architectural)
if config.get("pdf_type") and config.get("pdf_type") != pdf_type:
continue
score = sum(1 for kw in config.get("drawing_keywords", []) if kw.lower() in text_lower)
scores[ptype] = score
if not scores:
return {"detected_type": "unknown", "confidence": "low", "items": []}
best = max(scores, key=scores.get)
score = scores[best]
return {
"detected_type": best if score > 0 else "unknown",
"confidence": "high" if score >= 1 else "low",
"items": PAGE_ITEMS_MAP.get(best, {}).get("extract_items", []) if score > 0 else [],
}
|