Looking for n8n Expert – OCR workflow to sort images by SN1234

Kornel_Suszynski · August 4, 2025, 7:23am

Project Description:

I’m looking for an experienced n8n workflow developer to build an automation that:

Scans image files from a local folder or cloud storage (e.g. Dropbox, Google Drive),

Uses OCR (e.g. Tesseract.js or OCR.space) to detect a serial number in the format:

SN followed by 4 or 5 digits (e.g. SN1234 or SN12345),

If a valid serial number is detected:

Automatically creates a folder named after the number (e.g. SN1234),

Moves the corresponding image file into that folder,

If no valid SN number is found, the file should be left untouched in the input directory.

Technical Requirements:

Self-hosted or local n8n instance,

Use of OCR (Tesseract.js via community node or OCR.space API),

File handling (local disk or cloud integration: Dropbox/Google Drive),

Function Node to extract the serial number using regex: SN\d{4,5},

Conditional logic (IF Node), dynamic folder creation, file moving.

Input:

A folder containing .jpg / .png files (or cloud input),

Each image triggers a single execution.

Output:

Folders like SN1234/, SN56789/ are created dynamically,

Images are sorted into folders according to detected SN numbers.

Additional Info:

The workflow should run automatically (e.g. via CRON trigger or webhook).

Optional: log each match to Google Sheets or send a daily report email.

Ideal Candidate:

Solid experience with n8n and its workflow logic,

Familiar with OCR workflows and regex extraction,

Fast communication and ability to test locally.

Budget:

Open to offers – please suggest a total price for the full solution and optionally for ongoing support.

Contact:

Send me a short message with your experience and estimated delivery time.

jabbson · August 6, 2025, 6:18am

Below is my take on this.

Create an api wrapper for tesseract and dockerize it.

Dockerfile:

FROM python:3.12-slim

# Install Tesseract
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    && apt-get clean

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy app
COPY app /app
WORKDIR /app

# Run API
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

requirements.txt

fastapi
uvicorn
pytesseract
python-multipart

app/main.py

from fastapi import FastAPI, File, Form, UploadFile
import pytesseract
from PIL import Image
import io

app = FastAPI()

@app.post("/ocr")
async def perform_ocr(file_id: str = Form(...), file: UploadFile = File(...)):
    image_bytes = await file.read()
    image = Image.open(io.BytesIO(image_bytes))
    text = pytesseract.image_to_string(image)
    return {"file_id": file_id, "text": text}

build the image

docker build -t tesseract-ocr-api .

create a service in docker compose

services:
  tesseract-ocr-api:
    image: tesseract-ocr-api:latest
    container_name: tesseract-ocr-api
    hostname: tesseract-ocr-api
    restart: unless-stopped
    networks:
      - n8n-infra
    environment:
      - PYTHONUNBUFFERED=1

My drive folder before running the flow:

GDrive folder

The workflow:

After running the workflow:

GDrive folder

The email report:

Email