new file: app.py

new file: model/gap_detection_model.pt
new file: requirements.txt

app.py

@@ -0,0 +1,168 @@
+import os
+import tempfile
+import uuid
+import warnings
+
+import gradio as gr
+import requests
+from PIL import Image
+
+from main import WorksheetSolver
+
+warnings.filterwarnings("ignore")
+
+ALLOWED_EXTENSIONS = {"png", "jpg", "jpeg", "webp", "bmp"}
+GAP_DETECTION_MODEL_PATH = "./model/gap_detection_model.pt"
+GAP_MODEL_URL = "https://github.com/Hawk3388/solver/releases/download/v1.1.0/gap_detection_model.pt"
+
+
+def ensure_gap_model() -> str:
+	os.makedirs("./model", exist_ok=True)
+	if os.path.exists(GAP_DETECTION_MODEL_PATH):
+		return GAP_DETECTION_MODEL_PATH
+
+	with requests.get(GAP_MODEL_URL, stream=True, timeout=60) as response:
+		response.raise_for_status()
+		with open(GAP_DETECTION_MODEL_PATH, "wb") as model_file:
+			for chunk in response.iter_content(chunk_size=8192):
+				if chunk:
+					model_file.write(chunk)
+
+	return GAP_DETECTION_MODEL_PATH
+
+
+def _is_allowed_image(filename: str) -> bool:
+	return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
+
+
+def solve_worksheet(
+	image_path: str,
+	model_name: str,
+	local: bool,
+	think: bool,
+	thinking_budget: int,
+	debug: bool,
+	experimental: bool,
+):
+	if not image_path:
+		raise gr.Error("Please upload an image first.")
+
+	if not _is_allowed_image(image_path):
+		raise gr.Error("Please upload a valid image file (PNG, JPG, JPEG, WEBP, BMP).")
+
+	try:
+		model_path = ensure_gap_model()
+	except Exception as error:
+		raise gr.Error(f"Could not load the gap detection model: {error}") from error
+
+	with tempfile.TemporaryDirectory() as tmp_dir:
+		unique_id = uuid.uuid4().hex
+		input_path = os.path.join(tmp_dir, f"{unique_id}.png")
+		output_path = os.path.join(tmp_dir, f"{unique_id}_solved.png")
+
+		try:
+			Image.open(image_path).convert("RGB").save(input_path)
+
+			solver = WorksheetSolver(
+				input_path,
+				gap_detection_model_path=model_path,
+				llm_model_name=model_name.strip() or "gemini-2.5-flash",
+				think=think,
+				local=local,
+				thinking_budget=int(thinking_budget),
+				debug=debug,
+				experimental=experimental,
+			)
+
+			gaps, detected_image = solver.detect_gaps()
+			if not gaps:
+				raise gr.Error("No gaps were detected. Please try a clearer worksheet image.")
+
+			marked_image = solver.mark_gaps(detected_image, gaps)
+			solutions = solver.solve_all_gaps(marked_image)
+
+			if not solutions:
+				raise gr.Error("The AI could not find any solutions.")
+
+			solver.fill_gaps_in_image(input_path, solutions, output_path=output_path)
+
+			solved_image = Image.open(output_path).copy()
+			return solved_image
+
+		except Exception as error:
+			raise gr.Error(f"Processing error: {error}") from error
+
+
+def build_app() -> gr.Blocks:
+	with gr.Blocks(title="Worksheet Solver", css="""
+		.app-shell {max-width: 1200px; margin: 0 auto;}
+		.hero {text-align: center; margin: 14px 0 8px;}
+		.hero h1 {font-size: 2rem; margin-bottom: 6px;}
+		.hero p {opacity: 0.85;}
+	""") as demo:
+		gr.HTML(
+			"""
+			<div class='hero'>
+				<h1>Worksheet Solver</h1>
+				<p>Upload a worksheet image, configure the options, and generate the solved version.</p>
+			</div>
+			"""
+		)
+
+		with gr.Row(elem_classes=["app-shell"]):
+			with gr.Column(scale=1):
+				image_input = gr.Image(
+					type="filepath",
+					label="Worksheet Image",
+					sources=["upload"],
+				)
+
+				model_name = gr.Textbox(
+					label="LLM Model Name",
+					value="gemini-2.5-flash",
+					placeholder="e.g. gemini-2.5-flash or qwen3.5:35b",
+				)
+
+				with gr.Row():
+					local = gr.Checkbox(label="Local Mode (Ollama)", value=False)
+					think = gr.Checkbox(label="Thinking", value=True)
+
+				thinking_budget = gr.Slider(
+					minimum=0,
+					maximum=8192,
+					step=1,
+					value=2048,
+					label="Thinking Budget",
+					info="Only relevant when Thinking is enabled.",
+				)
+
+				with gr.Row():
+					debug = gr.Checkbox(label="Debug Mode", value=False)
+					experimental = gr.Checkbox(label="Experimental Mode", value=False)
+
+				solve_button = gr.Button("Solve", variant="primary")
+
+			with gr.Column(scale=1):
+				image_output = gr.Image(type="pil", label="Solved Worksheet")
+
+		solve_button.click(
+			fn=solve_worksheet,
+			inputs=[
+				image_input,
+				model_name,
+				local,
+				think,
+				thinking_budget,
+				debug,
+				experimental,
+			],
+			outputs=image_output,
+		)
+
+	return demo
+
+
+demo = build_app()
+
+if __name__ == "__main__":
+	demo.queue().launch(server_name="0.0.0.0", server_port=int(os.getenv("PORT", "7860")), share=True)

model/gap_detection_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09d72ab83480428164c040356af5dce6b59fd42d305621901d9d234f0657c09
+size 53210085

requirements.txt

@@ -0,0 +1,98 @@
+aiofiles==24.1.0
+altgraph==0.17.5
+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.12.1
+blinker==1.9.0
+brotli==1.2.0
+certifi==2026.2.25
+cffi==2.0.0
+charset-normalizer==3.4.5
+click==8.3.1
+colorama==0.4.6
+contourpy==1.3.2
+cryptography==46.0.5
+cycler==0.12.1
+distro==1.9.0
+exceptiongroup==1.3.1
+fastapi==0.135.1
+ffmpy==1.0.0
+filelock==3.25.0
+Flask==3.1.3
+fonttools==4.61.1
+fsspec==2026.2.0
+google-auth==2.49.0
+google-genai==1.66.0
+gradio==6.9.0
+gradio_client==2.3.0
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.4.2
+httpcore==1.0.9
+httpx==0.28.1
+huggingface_hub==1.7.1
+idna==3.11
+itsdangerous==2.2.0
+Jinja2==3.1.6
+kiwisolver==1.4.9
+lap==0.5.13
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+matplotlib==3.10.8
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==2.2.6
+ollama==0.6.1
+opencv-python==4.13.0.92
+orjson==3.11.7
+packaging==25.0
+pandas==2.3.3
+pefile==2024.8.26
+pillow==12.1.1
+polars==1.38.1
+polars-runtime-32==1.38.1
+psutil==7.2.2
+pyasn1==0.6.2
+pyasn1_modules==0.4.2
+pycparser==3.0
+pydantic==2.12.5
+pydantic_core==2.41.5
+pydub==0.25.1
+Pygments==2.19.2
+pyinstaller==6.19.0
+pyinstaller-hooks-contrib==2026.2
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.2.2
+python-multipart==0.0.22
+pytz==2026.1.post1
+pywin32-ctypes==0.2.3
+PyYAML==6.0.3
+requests==2.32.5
+rich==14.3.3
+rsa==4.9.1
+safehttpx==0.1.7
+scipy==1.15.3
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.52.1
+sympy==1.14.0
+tenacity==9.1.4
+tomlkit==0.13.3
+torch==2.10.0
+torchvision==0.25.0
+tqdm==4.67.3
+typer==0.24.1
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.3
+ultralytics==8.4.21
+ultralytics-thop==2.0.18
+urllib3==2.6.3
+uvicorn==0.41.0
+waitress==3.0.2
+websockets==16.0
+Werkzeug==3.1.6