OCR and Node Code error

[jamal]

Dear,

I follow this template to use OCR to save data on Vector Store,

Build a PDF Document RAG System with Mistral OCR, Qdrant and Gemini AI | n8n...

On the node “Code”, i get message error:

Where is the problem please? What is the equivalent python code?
Of more, i need to use Http request to use OCR before save on VectorStore or there are Nodes can be use to detect characters by OCRs?

Information on your n8n setup

• **n8n version:1.98.1
• Database (default: SQLite):
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• **Running n8n via (Docker, npm, n8n cloud, desktop app):Docker
• **Operating system:Win10

[Sudhanshu_Sharma]

Hey @jamal ,

Try to replace the first line of code with the following:-

$("Mistral DOC OCR").item.json.pages ;

and the run again, and let me know if it works or not .

: )

[jamal]

@Sudhanshu_Sharma

$("Mistral DOC OCR").item.json.pages ;

I set your line:

[Sudhanshu_Sharma]

Hey @jamal , yes yes it will show that red line in code but no worries it does not affect anything.

Please try to run this and add a trigger node before starting the workflow as I am able to see the error you got now is because you have not attached trigger node before running this node.

[jamal]

Dear, i get this message:

[Sudhanshu_Sharma]

Hey @jamal ,

Let’s do one thing. Please share the 2 nodes with me, let me have look at my side.

Follow these steps:-

1. First Open Mistral Doc OCR node and pin the output
2. Then copy this node as well the code node.
3. Paste these node over here.

I will have a look at this my side…

This way we can quickly solve this !

[jamal]

Finally, i use this code:

const data = $json.pages ;

return data.map(entry => ({
  json: {
    markdown: entry.markdown
  }
}));

it’s works fine now.