Tesseract OCR in n8n

[Sushant_Charaya]

The problem/error/question

I need to run OCR on images/PDFs inside an n8n workflow. I found the community node n8n-nodes-tesseractjs(Tesseract OCR), However, in my case, I’m unable to install community nodes. I’m looking for either:

1. Steps to enable/install this community node on my setup, or

2. A recommended workaround to use Tesseract OCR (or an equivalent OCR) in n8n without community nodes.

[jabbson]

I recently was helping someone to use tesseract, take a look at the following post:

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

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 uvico…