I need an OCR machine that can extract all text from a PDF file. We often receive files in PDF format that are essentially just images without text, which is why our own “PDF reader” in n8n doesn’t always work. I need it to do that.
It’s about receiving large annual reports with lots of columns in PDF format, and we need data from some of those columns.
For example, like in the image, where we need to use these columns as JSON.
I am pretty new, so explain in it to me, like I’m a child 
Since it’s an image you need an OCR node as you said. n8n Does not have an official node but there is a community one: n8n-nodes-tesseractjs
After extracting the text from image you can use different methods to filter them. I always use a ‘Code’ node to do so but you can use an AI node too if you don’t mind spending extra tokens.
In my opinion Mistral AI’s OCR tool is the best out there right now. Ideally you would use their API in a HTTP Request node to do your ocr transformation. If the data is sensitive, you can get a special license from them to use a private on prem instance for better privacy
If you need an example then I can build a demo
If you just need to turn those image‑based PDFs into actual text/structured data (like JSON), try Mathpix: https://mathpix.com/pdf-conversion. It does OCR on scanned PDFs and can extract tables/columns cleanly, then you can grab the data as JSON for n8n. Way less painful than trying to hack it with a basic PDF reader.
We can go with the vision models of OpenAI/Ollama to analyze the image, that will extract everything. and then we can keep the required data.
For dense tables in annual report PDFs, vision models (GPT-4o or Gemini Flash) work well but the key is the prompt. Pass the image with something like: "Extract all data from this table and return a JSON array where each row is an object with column headers as keys." - that reliably gets structured output without post-processing. For multi-page PDFs, split the file into individual page images first using the Extract Document Content node or a Code node, then run each page through the vision model and merge the results at the end.
The Mistral OCR API has a free tier (via their API console at console.mistral.ai). For a fully free and self-hostable option, the n8n-nodes-tesseractjs community node works well for image-based PDFs - you can pair it with a Convert to File node to pass the binary. If you want a cloud API with a generous free tier, Google Document AI is an option too, but the setup is more involved than Mistral’s single HTTP call approach.
