Spaces:
Sleeping
Sleeping
File size: 1,863 Bytes
19907be |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
from fastapi import FastAPI, UploadFile, File, HTTPException
from fastapi.responses import JSONResponse
import shutil
import os
from uuid import uuid4
from marker.converters.pdf import PdfConverter
from marker.models import create_model_dict
from marker.output import text_from_rendered
from threading import Lock
app = FastAPI()
# Singleton class for PdfConverter
class PdfConverterSingleton:
_instance = None
_lock = Lock()
def __new__(cls):
if cls._instance is None:
with cls._lock:
if cls._instance is None:
instance = super().__new__(cls)
instance._initialize()
cls._instance = instance
return cls._instance
def _initialize(self):
self.converter = PdfConverter(artifact_dict=create_model_dict())
def get_text(self, pdf_path: str) -> str:
rendered = self.converter(pdf_path)
text, _, _ = text_from_rendered(rendered)
return str(text)
# API function to call converter
def extract_text_from_pdf(pdf_path: str) -> str:
return PdfConverterSingleton().get_text(pdf_path)
# Endpoint to upload a file and extract markdown text
@app.post("/extract-pdf-text")
async def extract_pdf_text(file: UploadFile = File(...)):
if file.content_type != "application/pdf":
raise HTTPException(status_code=400, detail="Only PDF files are supported.")
temp_filename = f"/tmp/{uuid4().hex}.pdf"
try:
with open(temp_filename, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
text = extract_text_from_pdf(temp_filename)
return JSONResponse(content={"markdown_text": text})
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
finally:
if os.path.exists(temp_filename):
os.remove(temp_filename)
|