[Python] Azure Container-App Post-Request returns "502 Bad Gateway", "507 Insufficient...

I have a Azure Container-App containing an Docker Image of an Fast-API application that is supposed to alter an uploaded PDF and return back the altered PDF. On my localhost the application runs fine, however after deployment the Post-Request leads to the above responses. It says: upstream connect error or disconnect/reset before headers. reset reason: connection termination

However, the simple Hello-World-Get-Request works just fine so that the deployment should have worked.

The Protocol Stream does not contain any useful information.

I am helpful for any help, since I am not super experienced using Azure.

main.py

from fastapi import FastAPI, HTTPException, File, UploadFile
import logging
import io
from app.redact_pdf import redact_pdf
from fastapi.responses import StreamingResponse

app = FastAPI()

@app.post("/http_trigger")
async def http_trigger(file: UploadFile = File(...), language: str = None):
logging.info('FastAPI HTTP trigger function processed a request.')

if file.content_type == 'application/pdf':
input_pdf_stream = io.BytesIO(await file.read())

if not language:
raise HTTPException(status_code=400, detail="The request does not contain language parameter.")

# Verwenden Sie die redact_pdf Funktion mit den PDF Streams
output_pdf_stream = redact_pdf(input_pdf_stream, language)

# Erstellen Sie eine Response mit dem PDF-Stream
return StreamingResponse(
io.BytesIO(output_pdf_stream.read()),
media_type="application/pdf"
)
else:
raise HTTPException(status_code=400, detail="The request does not contain PDF data.")

@app.get("/hello")
async def read_root():
return {"message": "hello world"}


redact_pdf.py

import pymupdf
import re
import io
import cv2
import numpy as np
from flair.data import Sentence
from flair.models import SequenceTagger

def redact_pdf(input_pdf_stream, language):
if language not in ["EN", "DE"]:
raise ValueError("Invalid language selection. Please choose 'EN' for English or 'DE' for German.")

if language == "EN":
tagger = SequenceTagger.load("flair/ner-english-large")
else:
tagger = SequenceTagger.load("flair/ner-german-large")
Open PDF from BytesIO-Stream
doc = pymupdf.open("pdf", input_pdf_stream)

zip_code_pattern = re.compile(r'\b\d{5}\b') # Beispiel: 12345
email_pattern = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')

phone_patterns = [
re.compile(r'\b\d{3}[-.\s]?\d{3}[-.\s]?\d{4}\b'), # 123-456-7890 oder 123 456 7890
re.compile(r'\(\d{3}\)\s*\d{3}[-.\s]?\d{4}\b'), # (123) 456-7890
re.compile(r'\b\d{4}[-.\s]?\d{3}[-.\s]?\d{3}\b'), # 1234-567-890
]

for page_num in range(len(doc)):
page = doc.load_page(page_num)
text = page.get_text()

sentence = Sentence(text)
tagger.predict(sentence)

entities = [(entity.start_position, entity.end_position, entity.text) for entity in sentence.get_spans('ner') if entity.tag in ["PER", "ORG", "LOC"]]

for match in zip_code_pattern.finditer(text):
start, end = match.span()
entities.append((start, end, match.group()))

for pattern in phone_patterns:
for match in pattern.finditer(text):
start, end = match.span()
entities.append((start, end, match.group()))

for match in email_pattern.finditer(text):
start, end = match.span()
entities.append((start, end, match.group()))

print(entities)

for start, end, entity_text in entities:
search_results = page.search_for(entity_text)
if search_results:
for rect in search_results:
page.add_redact_annot(rect, text="REDACTED", fill=(0, 0, 0))

page.apply_redactions()

pix = page.get_pixmap()
img = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.height, pix.width, pix.n)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2)

contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
if 30 < w < 400 and 5 < h < 150:
page.add_redact_annot(pymupdf.Rect(x, y, x+w, y+h), text="REDACTED", fill=(0, 0, 0))

page.apply_redactions()

output_pdf_stream = io.BytesIO()
doc.save(output_pdf_stream, garbage=4, deflate=True, clean=True)
output_pdf_stream.seek(0)

return output_pdf_stream


Dockerfile

# Start with the official Python image
FROM python:3.9-slim

# Set the working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update \
&& apt-get install --no-install-recommends -y \
gcc \
build-essential \
libgl1-mesa-glx \
libglib2.0-0 \
&& apt-get clean

# Install python packages
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the application code
COPY . .

# Expose the port the app runs on
EXPOSE 8000

# Command to run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

Continue reading...