34da9f4cda
backend-lehrer (11 files): - llm_gateway/routes/schools.py (867 → 5), recording_api.py (848 → 6) - messenger_api.py (840 → 5), print_generator.py (824 → 5) - unit_analytics_api.py (751 → 5), classroom/routes/context.py (726 → 4) - llm_gateway/routes/edu_search_seeds.py (710 → 4) klausur-service (12 files): - ocr_labeling_api.py (845 → 4), metrics_db.py (833 → 4) - legal_corpus_api.py (790 → 4), page_crop.py (758 → 3) - mail/ai_service.py (747 → 4), github_crawler.py (767 → 3) - trocr_service.py (730 → 4), full_compliance_pipeline.py (723 → 4) - dsfa_rag_api.py (715 → 4), ocr_pipeline_auto.py (705 → 4) website (6 pages): - audit-checklist (867 → 8), content (806 → 6) - screen-flow (790 → 4), scraper (789 → 5) - zeugnisse (776 → 5), modules (745 → 4) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
85 lines
3.0 KiB
Python
85 lines
3.0 KiB
Python
"""
|
|
OCR Pipeline Auto-Mode Helpers.
|
|
|
|
VLM shear detection, SSE event formatting, and request models.
|
|
|
|
Lizenz: Apache 2.0
|
|
DATENSCHUTZ: Alle Verarbeitung erfolgt lokal.
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
import os
|
|
import re
|
|
from typing import Any, Dict
|
|
|
|
from pydantic import BaseModel
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class RunAutoRequest(BaseModel):
|
|
from_step: int = 1 # 1=deskew, 2=dewarp, 3=columns, 4=rows, 5=words, 6=llm-review
|
|
ocr_engine: str = "auto" # "auto" | "rapid" | "tesseract"
|
|
pronunciation: str = "british"
|
|
skip_llm_review: bool = False
|
|
dewarp_method: str = "ensemble" # "ensemble" | "vlm" | "cv"
|
|
|
|
|
|
async def auto_sse_event(step: str, status: str, data: Dict[str, Any]) -> str:
|
|
"""Format a single SSE event line."""
|
|
payload = {"step": step, "status": status, **data}
|
|
return f"data: {json.dumps(payload)}\n\n"
|
|
|
|
|
|
async def detect_shear_with_vlm(image_bytes: bytes) -> Dict[str, Any]:
|
|
"""Ask qwen2.5vl:32b to estimate the vertical shear angle of a scanned page.
|
|
|
|
The VLM is shown the image and asked: are the column/table borders tilted?
|
|
If yes, by how many degrees? Returns a dict with shear_degrees and confidence.
|
|
Confidence is 0.0 if Ollama is unavailable or parsing fails.
|
|
"""
|
|
import httpx
|
|
import base64
|
|
|
|
ollama_base = os.getenv("OLLAMA_BASE_URL", "http://host.docker.internal:11434")
|
|
model = os.getenv("OLLAMA_HTR_MODEL", "qwen2.5vl:32b")
|
|
|
|
prompt = (
|
|
"This is a scanned vocabulary worksheet. Look at the vertical borders of the table columns. "
|
|
"Are they perfectly vertical, or do they tilt slightly? "
|
|
"If they tilt, estimate the tilt angle in degrees (positive = top tilts right, negative = top tilts left). "
|
|
"Reply with ONLY a JSON object like: {\"shear_degrees\": 1.2, \"confidence\": 0.8} "
|
|
"Use confidence 0.0-1.0 based on how clearly you can see the tilt. "
|
|
"If the columns look straight, return {\"shear_degrees\": 0.0, \"confidence\": 0.9}"
|
|
)
|
|
|
|
img_b64 = base64.b64encode(image_bytes).decode("utf-8")
|
|
payload = {
|
|
"model": model,
|
|
"prompt": prompt,
|
|
"images": [img_b64],
|
|
"stream": False,
|
|
}
|
|
|
|
try:
|
|
async with httpx.AsyncClient(timeout=60.0) as client:
|
|
resp = await client.post(f"{ollama_base}/api/generate", json=payload)
|
|
resp.raise_for_status()
|
|
text = resp.json().get("response", "")
|
|
|
|
# Parse JSON from response (may have surrounding text)
|
|
match = re.search(r'\{[^}]+\}', text)
|
|
if match:
|
|
data = json.loads(match.group(0))
|
|
shear = float(data.get("shear_degrees", 0.0))
|
|
conf = float(data.get("confidence", 0.0))
|
|
# Clamp to reasonable range
|
|
shear = max(-3.0, min(3.0, shear))
|
|
conf = max(0.0, min(1.0, conf))
|
|
return {"method": "vlm_qwen2.5vl", "shear_degrees": round(shear, 3), "confidence": round(conf, 2)}
|
|
except Exception as e:
|
|
logger.warning(f"VLM dewarp failed: {e}")
|
|
|
|
return {"method": "vlm_qwen2.5vl", "shear_degrees": 0.0, "confidence": 0.0}
|