init: ocr-service (async FastAPI with EasyOCR; PDF support)

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.env

Dockerfile

@@ -0,0 +1,42 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+FROM python:3.12-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=off \
+    UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy \
+    UV_PROJECT_ENVIRONMENT=/opt/app-root \
+    OMP_NUM_THREADS=4 \
+    CMAKE_BUILD_PARALLEL_LEVEL=4
+
+# System deps for easyocr (opencv, tesseract data optional)
+RUN apt-get update -y && apt-get install -y --no-install-recommends \
+    build-essential \
+    libgl1 \
+    libglib2.0-0 \
+    curl ca-certificates && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install uv
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    /root/.cargo/bin/uv --version
+
+WORKDIR /app
+
+# Copy project metadata and source
+COPY pyproject.toml /app/pyproject.toml
+COPY src /app/src
+
+# Sync dependencies into project env
+RUN /root/.cargo/bin/uv sync --frozen
+
+# Create cache volume for EasyOCR
+VOLUME ["/cache"]
+
+# Expose and healthcheck
+EXPOSE 7860
+HEALTHCHECK --interval=20s --timeout=5s --start-period=10s --retries=5 \
+  CMD sh -c 'curl -fsS http://127.0.0.1:${PORT:-7860}/ping > /dev/null || exit 1'
+
+ENV PORT=7860
+CMD ["/root/.cargo/bin/uv", "run", "uvicorn", "ocr_service.app:app", "--host", "0.0.0.0", "--port", "${PORT}"] 

README.md

@@ -0,0 +1,12 @@
+---
+title: Docling Serializer
+emoji: 🏢
+colorFrom: purple
+colorTo: purple
+sdk: docker
+app_port: 7860
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

pyproject.toml

@@ -0,0 +1,19 @@
+[project]
+name = "ocr-service"
+version = "0.1.0"
+description = "FastAPI OCR service with EasyOCR and OnnxTR (stub)"
+requires-python = ">=3.10"
+dependencies = [
+  "fastapi>=0.115.0",
+  "uvicorn[standard]>=0.30.0",
+  "easyocr>=1.7.2",
+  "opencv-python-headless>=4.10.0.84",
+  "pymupdf>=1.24.10",
+  "pillow>=10.3.0",
+  "python-multipart>=0.0.9",
+  "pydantic>=2.7.0",
+  "requests>=2.32.0"
+]
+
+[tool.uv]
+index-url = "https://pypi.org/simple" 

requirements.txt

@@ -0,0 +1,2 @@
+fastapi
+uvicorn[standard] 

src/ocr_service/__init__.py

@@ -0,0 +1 @@
+__all__ = [] 

src/ocr_service/app.py

@@ -0,0 +1,76 @@
+import io
+import os
+from enum import Enum
+from typing import List
+
+import requests
+import fitz  # PyMuPDF
+from fastapi import FastAPI, UploadFile, File, Form, HTTPException
+from fastapi.responses import JSONResponse
+
+app = FastAPI(title="OCR Service", version="0.1.0")
+
+class OcrEngine(str, Enum):
+	EASYOCR = "easyocr"
+	ONNXTR = "onnxtr"
+
+
+def get_easyocr_reader(lang: str = "en"):
+	import easyocr
+	cache_dir = os.environ.get("EASYOCR_CACHE", "/cache/EasyOcr")
+	os.makedirs(cache_dir, exist_ok=True)
+	return easyocr.Reader([lang], gpu=True, model_storage_directory=cache_dir)
+
+
+def pdf_bytes_to_images(pdf_bytes: bytes, dpi: int = 200) -> List[bytes]:
+	doc = fitz.open(stream=pdf_bytes, filetype="pdf")
+	images: List[bytes] = []
+	for page in doc:
+		mat = fitz.Matrix(dpi / 72.0, dpi / 72.0)
+		pix = page.get_pixmap(matrix=mat)
+		images.append(pix.tobytes("png"))
+	doc.close()
+	return images
+
+
+@app.get("/ping")
+async def ping() -> dict:
+	return {"status": "ok"}
+
+
+@app.post("/ocr/url")
+async def ocr_from_url(url: str = Form(...), engine: OcrEngine = Form(OcrEngine.EASYOCR), lang: str = Form("en")):
+	if engine == OcrEngine.ONNXTR:
+		raise HTTPException(status_code=501, detail="OnnxTR engine not yet wired. Use engine=easyocr.")
+	try:
+		resp = requests.get(url, timeout=30)
+		resp.raise_for_status()
+		content = resp.content
+		reader = get_easyocr_reader(lang)
+		lines: List[str] = []
+		if resp.headers.get("content-type", "").lower().startswith("application/pdf") or url.lower().endswith(".pdf"):
+			for img in pdf_bytes_to_images(content):
+				lines.extend(reader.readtext(img, detail=0))
+		else:
+			lines = reader.readtext(content, detail=0)
+		return {"engine": engine, "lang": lang, "lines": lines}
+	except Exception as e:
+		raise HTTPException(status_code=400, detail=str(e))
+
+
+@app.post("/ocr/file")
+async def ocr_from_file(file: UploadFile = File(...), engine: OcrEngine = Form(OcrEngine.EASYOCR), lang: str = Form("en")):
+	if engine == OcrEngine.ONNXTR:
+		raise HTTPException(status_code=501, detail="OnnxTR engine not yet wired. Use engine=easyocr.")
+	try:
+		data = await file.read()
+		reader = get_easyocr_reader(lang)
+		lines: List[str] = []
+		if file.filename.lower().endswith(".pdf"):
+			for img in pdf_bytes_to_images(data):
+				lines.extend(reader.readtext(img, detail=0))
+		else:
+			lines = reader.readtext(data, detail=0)
+		return {"engine": engine, "lang": lang, "lines": lines}
+	except Exception as e:
+		raise HTTPException(status_code=400, detail=str(e))