mirror of
https://github.com/snapotter-hq/SnapOtter.git
synced 2026-08-03 07:46:42 +02:00
feat: add Phase 4 AI tools with Python bridge and 6 new tools
Add Python bridge (packages/ai/src/bridge.ts) that calls Python scripts via child_process with venv-first fallback to system python3. Implements 6 AI-powered tools: - Remove Background: rembg-based with U2-Net/IS-Net models - Image Upscaling: Real-ESRGAN with Lanczos fallback - OCR/Text Extraction: Tesseract + PaddleOCR engines - Face/PII Blur: MediaPipe face detection with configurable blur - Object Eraser: LaMa inpainting with mask-based input - Smart Crop: Sharp attention-based entropy cropping (no Python needed) Each tool includes: Python script, TypeScript wrapper, API route, and React settings component. All Python scripts handle ImportError gracefully with clear installation messages.
This commit is contained in:
@@ -0,0 +1,81 @@
|
||||
"""Text extraction from images using Tesseract or PaddleOCR."""
|
||||
import sys
|
||||
import json
|
||||
|
||||
|
||||
def main():
|
||||
input_path = sys.argv[1]
|
||||
settings = json.loads(sys.argv[2]) if len(sys.argv) > 2 else {}
|
||||
|
||||
engine = settings.get("engine", "tesseract")
|
||||
language = settings.get("language", "en")
|
||||
|
||||
try:
|
||||
if engine == "paddleocr":
|
||||
try:
|
||||
from paddleocr import PaddleOCR
|
||||
|
||||
ocr = PaddleOCR(use_angle_cls=True, lang=language)
|
||||
result = ocr.ocr(input_path, cls=True)
|
||||
text = "\n".join(
|
||||
[
|
||||
line[1][0]
|
||||
for res in result
|
||||
if res
|
||||
for line in res
|
||||
if line and line[1]
|
||||
]
|
||||
)
|
||||
print(
|
||||
json.dumps({"success": True, "text": text, "engine": "paddleocr"})
|
||||
)
|
||||
except ImportError:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": "PaddleOCR is not installed. Install with: pip install paddleocr paddlepaddle",
|
||||
}
|
||||
)
|
||||
)
|
||||
sys.exit(1)
|
||||
else:
|
||||
# Tesseract via subprocess
|
||||
import subprocess
|
||||
|
||||
lang_map = {"en": "eng", "de": "deu", "fr": "fra", "es": "spa", "zh": "chi_sim", "ja": "jpn", "ko": "kor"}
|
||||
tess_lang = lang_map.get(language, "eng")
|
||||
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["tesseract", input_path, "stdout", "-l", tess_lang],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=120,
|
||||
)
|
||||
text = result.stdout.strip()
|
||||
if result.returncode != 0 and not text:
|
||||
raise RuntimeError(result.stderr.strip() or "Tesseract failed")
|
||||
print(
|
||||
json.dumps(
|
||||
{"success": True, "text": text, "engine": "tesseract"}
|
||||
)
|
||||
)
|
||||
except FileNotFoundError:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": "Tesseract is not installed. Install with: apt-get install tesseract-ocr",
|
||||
}
|
||||
)
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
except Exception as e:
|
||||
print(json.dumps({"success": False, "error": str(e)}))
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user