Description
Extract text from a PDF. First try pdf-parse (free, fast); if the result is low quality (scanned PDF, poor OCR), fall back to Claude Sonnet vision (requires an Anthropic API key in Settings → AI Providers).
action_pdf_parse · action · Files & Documents · Available · v1.0.0
Extract text from a PDF. First try pdf-parse (free, fast); if the result is low quality (scanned PDF, poor OCR), fall back to Claude Sonnet vision (requires an Anthropic API key in Settings → AI Providers).
Fields shown in the editor when configuring the node. Generated directly from the NodeDefconfigFields.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
pathFile PDF su disco (opzionale) | file-picker | no | — es. ordine.pdf o {{input.attachment.path}} | Path nel sandbox del tenant. Se vuoto, l'engine cerca i bytes in "Base64" qui sotto. Uno dei due è obbligatorio. |
base64Base64 dei bytes PDF (opzionale) | expression | no | — {{$node.ImapTrigger.json.attachments[0].base64}} | Stringa base64 del PDF (es. allegato email). Massimo 32 MB. Si usa quando il PDF arriva via webhook/email senza essere salvato su disco. |
modeStrategia estrazione | enumautopdf-parse-onlyllm-only | no | auto | auto = prova pdf-parse, fa fallback LLM-vision se la qualità è bassa (raccomandato). pdf-parse-only = solo libreria gratis, niente API LLM (costo zero, ma fallisce su PDF scannerizzati). llm-only = salta pdf-parse e va diretto su Claude Sonnet (massima qualità, max costo per call). |
Fields available to downstream nodes via $node.<alias>.json.<field>:
textconfidencemodepagessizeBytesusedLlmFallbackllmModelcheapAttemptJSON snippet of the node as it appears in the workflow. Values are derived fromdefaultValue and from required parameters.
{
"id": "node-action_pdf_parse-1",
"defId": "action_pdf_parse",
"label": "PDF: Parse (text extraction)",
"config": {
"mode": "auto"
}
}Available now on all FlowForge plans. Try it free without a credit card.
Start freeBrowse all nodes