first commit

main.py

@@ -0,0 +1,81 @@
+import os
+import tempfile
+from typing import Optional
+
+from fastapi import FastAPI, File, HTTPException, UploadFile
+from marker.config.parser import ConfigParser
+from marker.converters.pdf import PdfConverter
+from marker.models import create_model_dict
+from marker.output import text_from_rendered
+
+app = FastAPI()
+converter: Optional[PdfConverter] = None
+
+
+@app.on_event("startup")
+async def startup_event() -> None:
+    global converter
+
+    config = {
+        "output_format": "markdown",
+        "force_ocr": True,
+        "use_llm": False,
+    }
+
+    config_parser = ConfigParser(config)
+
+    converter = PdfConverter(
+        config=config_parser.generate_config_dict(),
+        artifact_dict=create_model_dict(),
+        processor_list=config_parser.get_processors(),
+        renderer=config_parser.get_renderer(),
+        llm_service=config_parser.get_llm_service(),
+    )
+
+
+@app.post("/extract")
+async def extract(file: UploadFile = File(...)) -> dict[str, str]:
+    if file.content_type not in {
+        "application/pdf",
+        "image/png",
+        "image/jpeg",
+        "image/tiff",
+    }:
+        raise HTTPException(
+            status_code=400,
+            detail="File must be a PDF or image (png/jpeg/tiff).",
+        )
+
+    if converter is None:
+        raise HTTPException(
+            status_code=500,
+            detail="OCR engine not initialized.",
+        )
+
+    temp_path = None
+    try:
+        suffix = os.path.splitext(file.filename)[1].lower() or ".pdf"
+        if suffix not in {".pdf", ".png", ".jpg", ".jpeg", ".tif", ".tiff"}:
+            suffix = ".pdf"
+
+        with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
+            temp_path = tmp.name
+            tmp.write(await file.read())
+
+        rendered = converter(temp_path)
+        markdown_text, _, _ = text_from_rendered(rendered)
+
+        return {"markdown": markdown_text}
+
+    except Exception as exc:
+        raise HTTPException(
+            status_code=500,
+            detail=f"OCR extraction failed: {exc}",
+        ) from exc
+
+    finally:
+        if temp_path and os.path.exists(temp_path):
+            try:
+                os.remove(temp_path)
+            except OSError:
+                pass

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+python-multipart
+marker-pdf
+torch