# \#read-pdf

**URL:** https://community.n8n.io/tag/read-pdf/182.md

[Latest](https://community.n8n.io/latest.md) · [Categories](https://community.n8n.io/categories.md) · [Tags](https://community.n8n.io/tags.md)

---

## [Automatically fill forms from incoming emails?](https://community.n8n.io/t/automatically-fill-forms-from-incoming-emails/150721)

<div class="topic-metadata">

**Author:** [@Nelly\_gig](https://community.n8n.io/u/Nelly_gig)\
**Replies:** 4\
**Last updated:** [October 6, 2026, 6:45pm UTC](https://community.n8n.io/t/automatically-fill-forms-from-incoming-emails/150721 "2026-10-06T18:45:37Z")

</div>

Hi everyone, I’m trying to figure out if this kind of workflow is possible with n8n. We get a lot of emails from clients, we need to automatically extract that data and use it to fill out a PDF form we use regularly. On…

---

## [Turning PDF invoices into ZUGFeRD/XRechnung — a 22-node workflow, and the 7 mistakes I made](https://community.n8n.io/t/turning-pdf-invoices-into-zugferd-xrechnung-a-22-node-workflow-and-the-7-mistakes-i-made/310891)

<div class="topic-metadata">

**Author:** [@pie](https://community.n8n.io/u/pie)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 6:40pm UTC](https://community.n8n.io/t/turning-pdf-invoices-into-zugferd-xrechnung-a-22-node-workflow-and-the-7-mistakes-i-made/310891 "2026-09-02T18:40:46Z")

</div>

We had to solve a problem that a lot of German and EU companies will hit over the next 18 months: a mid-sized company writes its invoices in Word, and from 2027 it legally has to send structured e-invoices — ZUGFeRD fo…

---

## [PDF TO TEXT , DOCX TO TEXT, DOCS TO TEXT ( Free extract from pdf, docs and docx file )](https://community.n8n.io/t/pdf-to-text-docx-to-text-docs-to-text-free-extract-from-pdf-docs-and-docx-file/309281)

<div class="topic-metadata">

**Author:** [@sherazbintahir](https://community.n8n.io/u/sherazbintahir)\
**Replies:** 0\
**Last updated:** [August 24, 2026, 1:25pm UTC](https://community.n8n.io/t/pdf-to-text-docx-to-text-docs-to-text-free-extract-from-pdf-docs-and-docx-file/309281 "2026-08-24T13:25:08Z")

</div>

PDF TO TEXT , DOCX TO TEXT, DOCS TO TEXT FREE FILE EXTRACTOR NODE • PDF → Text • DOC → Text • DOCX → Text Node name:\*\* n8n-nodes-word-extractor You can install it directly from: n8n → Settings → Community Nodes → …

---

## [What’s your preferred way to handle PDFs in n8n workflows?](https://community.n8n.io/t/what-s-your-preferred-way-to-handle-pdfs-in-n8n-workflows/307999)

<div class="topic-metadata">

**Author:** [@Rishabh\_Dugar](https://community.n8n.io/u/Rishabh_Dugar)\
**Replies:** 5\
**Last updated:** [August 19, 2026, 1:51am UTC](https://community.n8n.io/t/what-s-your-preferred-way-to-handle-pdfs-in-n8n-workflows/307999 "2026-08-19T01:51:44Z")

</div>

I’ve been experimenting with workflows where PDFs need to be merged, split, protected, or processed automatically. One thing I noticed is that PDF handling can become a little messy when the workflow needs to deal with …

---

## [Built a PDF node that runs fully local (n8n-nodes-pdf)](https://community.n8n.io/t/built-a-pdf-node-that-runs-fully-local-n8n-nodes-pdf/303208)

<div class="topic-metadata">

**Author:** [@krystianslowik](https://community.n8n.io/u/krystianslowik)\
**Replies:** 1\
**Last updated:** [July 14, 2026, 12:35pm UTC](https://community.n8n.io/t/built-a-pdf-node-that-runs-fully-local-n8n-nodes-pdf/303208 "2026-07-14T12:35:57Z")

</div>

Hey everyone :waving\_hand: I built a PDF node and figured I’d share it here. The main idea is that everything runs locally on your instance. No API keys, per-page pricing, your documents don’t get uploaded anywhere. Th…

---

## [Generate PDFs from HTML in n8n (Step-by-Step Tutorial)](https://community.n8n.io/t/generate-pdfs-from-html-in-n8n-step-by-step-tutorial/301604)

<div class="topic-metadata">

**Author:** [@Rishabh\_Dugar](https://community.n8n.io/u/Rishabh_Dugar)\
**Replies:** 0\
**Last updated:** [July 1, 2026, 5:21am UTC](https://community.n8n.io/t/generate-pdfs-from-html-in-n8n-step-by-step-tutorial/301604 "2026-07-01T05:21:02Z")

</div>

If your workflow generates invoices, reports, contracts, certificates, or any document that starts as HTML, you’ll eventually need to convert it into a PDF. In this tutorial, I’ll show you how to generate PDFs directly …

---

## [Default Data Loader Error - pdf-parse v1 only](https://community.n8n.io/t/default-data-loader-error-pdf-parse-v1-only/298233)

<div class="topic-metadata">

**Author:** [@atawfic](https://community.n8n.io/u/atawfic)\
**Replies:** 7\
**Last updated:** [June 5, 2026, 4:22pm UTC](https://community.n8n.io/t/default-data-loader-error-pdf-parse-v1-only/298233 "2026-06-05T16:22:24Z")

</div>

Describe the problem/error/question Failed to load pdf-parse. This loader currently supports pdf-parse v1 only. Please install v1, e.g. npm install pdf-parse@^1 (v2 is not yet supported). Failed to load pdf-parse. This …

---

## [How to automate invoice PDF generation and email with Airtable in N8N](https://community.n8n.io/t/how-to-automate-invoice-pdf-generation-and-email-with-airtable-in-n8n/297410)

<div class="topic-metadata">

**Author:** [@roadfew](https://community.n8n.io/u/roadfew)\
**Replies:** 1\
**Last updated:** [May 29, 2026, 11:50am UTC](https://community.n8n.io/t/how-to-automate-invoice-pdf-generation-and-email-with-airtable-in-n8n/297410 "2026-05-29T11:50:16Z")

</div>

Want to automate invoice generation with n8n? This tutorial will show you how to pull invoice data from Airtable, generate a professional PDF using CustomJS Invoice Generator, send it to your client by ema…

---

## [PDF data extraction with AI guardrails and human-in-the-loop (Template)](https://community.n8n.io/t/pdf-data-extraction-with-ai-guardrails-and-human-in-the-loop-template/295552)

<div class="topic-metadata">

**Author:** [@Stig](https://community.n8n.io/u/Stig)\
**Replies:** 1\
**Last updated:** [May 13, 2026, 4:31pm UTC](https://community.n8n.io/t/pdf-data-extraction-with-ai-guardrails-and-human-in-the-loop-template/295552 "2026-05-13T16:31:42Z")

</div>

Hey community! I wanted to share a workflow (+ video!) I recently built for document data extraction in n8n using a node I recently published for Cradl AI (disclaimer: I work there). The example uses invoice processing…

---

## [Decrypting PDF and ZIP](https://community.n8n.io/t/decrypting-pdf-and-zip/19287)

<div class="topic-metadata">

**Author:** [@mokkin](https://community.n8n.io/u/mokkin)\
**Replies:** 2\
**Last updated:** [April 17, 2026, 1:21pm UTC](https://community.n8n.io/t/decrypting-pdf-and-zip/19287 "2026-04-17T13:21:55Z")

</div>

I’m fetching an email including a PDF and a ZIP file (that contains a CSV at the end). Both files are encrypted with the same password. I’d like to read the PDF and the zipped CSV, but I could’nt find an option in the cr…

---

## [CV & Resume Parser — Gmail to Airtable with job description matching, scoring, and Slack notification](https://community.n8n.io/t/cv-resume-parser-gmail-to-airtable-with-job-description-matching-scoring-and-slack-notification/280759)

<div class="topic-metadata">

**Author:** [@Terence\_Hielscher](https://community.n8n.io/u/Terence_Hielscher)\
**Replies:** 4\
**Last updated:** [April 2, 2026, 12:44pm UTC](https://community.n8n.io/t/cv-resume-parser-gmail-to-airtable-with-job-description-matching-scoring-and-slack-notification/280759 "2026-04-02T12:44:48Z")

</div>

Hey everyone Sharing an n8n workflow I built for a recruitment client who was spending 4 hours every week manually reading CVs before anyone could make a hiring decision. What this n8n CV parser does: A CV arrives by e…

---

## [PDF to vector database workflow with tables and images (n8n, embeddings, RAG, Qdrant/Weaviate, Supabase)](https://community.n8n.io/t/pdf-to-vector-database-workflow-with-tables-and-images-n8n-embeddings-rag-qdrant-weaviate-supabase/220658)

<div class="topic-metadata">

**Author:** [@pochta.butin](https://community.n8n.io/u/pochta.butin)\
**Replies:** 2\
**Last updated:** [February 5, 2026, 6:02pm UTC](https://community.n8n.io/t/pdf-to-vector-database-workflow-with-tables-and-images-n8n-embeddings-rag-qdrant-weaviate-supabase/220658 "2026-02-05T18:02:53Z")

</div>

How can all the information from a PDF, including text, tables, and images, be saved to a vector database, such as supabase vector, so that all data can be read in the future without exception? Help me find a suitable t…

---

## [Convert formatted markdown to PDFs without additional libraries or paid services](https://community.n8n.io/t/convert-formatted-markdown-to-pdfs-without-additional-libraries-or-paid-services/175125)

<div class="topic-metadata">

**Author:** [@trungtlt](https://community.n8n.io/u/trungtlt)\
**Replies:** 5\
**Last updated:** [January 26, 2026, 3:08pm UTC](https://community.n8n.io/t/convert-formatted-markdown-to-pdfs-without-additional-libraries-or-paid-services/175125 "2026-01-26T15:08:59Z")

</div>

I’ve just published a new workflow template that helps you automatically generate professional PDFs and share them with your team in Slack. It use custom HTTP request node to create document on Google Drive (with markdo…

---

## [Answer product queries via WhatsApp using OpenAI GPT-4o and PDF knowledge base](https://community.n8n.io/t/answer-product-queries-via-whatsapp-using-openai-gpt-4o-and-pdf-knowledge-base/250739)

<div class="topic-metadata">

**Author:** [@weblineindia](https://community.n8n.io/u/weblineindia)\
**Replies:** 0\
**Last updated:** [January 16, 2026, 6:10am UTC](https://community.n8n.io/t/answer-product-queries-via-whatsapp-using-openai-gpt-4o-and-pdf-knowledge-base/250739 "2026-01-16T06:10:13Z")

</div>

WhatsApp AI Sales Agent using PDF Vector Store This workflow turns your WhatsApp number into an intelligent AI-powered Sales Agent that answers product queries using real data extracted from a PDF brochure. It loads a pr…

---

## [WhatsApp AI Sales Agent (PDF-Powered)](https://community.n8n.io/t/whatsapp-ai-sales-agent-pdf-powered/239911)

<div class="topic-metadata">

**Author:** [@weblineindia](https://community.n8n.io/u/weblineindia)\
**Replies:** 0\
**Last updated:** [December 23, 2025, 6:49am UTC](https://community.n8n.io/t/whatsapp-ai-sales-agent-pdf-powered/239911 "2025-12-23T06:49:33Z")

</div>

This workflow turns your WhatsApp number into an AI-powered sales assistant that answers customer product questions using real data from a PDF brochure. It automatically: Loads a product brochure (PDF) Converts it…

---

## [Fill PDF Forms with n8n](https://community.n8n.io/t/fill-pdf-forms-with-n8n/193424)

<div class="topic-metadata">

**Author:** [@Micha0827](https://community.n8n.io/u/Micha0827)\
**Replies:** 1\
**Last updated:** [November 11, 2025, 8:51pm UTC](https://community.n8n.io/t/fill-pdf-forms-with-n8n/193424 "2025-11-11T20:51:38Z")

</div>

I have found no open source tool to fill PDF Forms. Thats why i make self :slight\_smile: I have build small api for read form fields from pdf and fill the fields. Source can be file or pdf Link (google docs for example). …

---

## [Update Excel template values from PDF + CSV (with light AI matching)](https://community.n8n.io/t/update-excel-template-values-from-pdf-csv-with-light-ai-matching/206040)

<div class="topic-metadata">

**Author:** [@Avy\_Perez](https://community.n8n.io/u/Avy_Perez)\
**Replies:** 0\
**Last updated:** [October 15, 2025, 9:00am UTC](https://community.n8n.io/t/update-excel-template-values-from-pdf-csv-with-light-ai-matching/206040 "2025-10-15T09:00:10Z")

</div>

Hi everyone, I want to build a straightforward n8n flow that updates values in an Excel template using data from a PDF financial statement and a CSV. The plan is: Read a CSV with the target rows (the template “skelet…

---

## [Need help finding a workflow template for Word → PDF automation](https://community.n8n.io/t/need-help-finding-a-workflow-template-for-word-pdf-automation/200116)

<div class="topic-metadata">

**Author:** [@Anirudh\_Tugawe](https://community.n8n.io/u/Anirudh_Tugawe)\
**Replies:** 0\
**Last updated:** [October 6, 2025, 3:45am UTC](https://community.n8n.io/t/need-help-finding-a-workflow-template-for-word-pdf-automation/200116 "2025-10-06T03:45:37Z")

</div>

Greatings of the day! I am trying to build a workflow where everything starts from an Excel file that gets uploaded to a Google Drive folder. Once the new file is added, I want the workflow to trigger automatically. Th…

---

## [Best way to fill PDF forms in an n8n workflow?](https://community.n8n.io/t/best-way-to-fill-pdf-forms-in-an-n8n-workflow/186814)

<div class="topic-metadata">

**Author:** [@bkell](https://community.n8n.io/u/bkell)\
**Replies:** 5\
**Last updated:** [September 24, 2025, 2:20pm UTC](https://community.n8n.io/t/best-way-to-fill-pdf-forms-in-an-n8n-workflow/186814 "2025-09-24T14:20:24Z")

</div>

Hi everyone, I’m working on a workflow where I need to take incoming data and files, use that information to fill out a PDF form we use regularly, and then continue the process by sending the completed PDF out by email …

---

## [Automated n8n workflow for analyzing, renaming, and AI-assisted processing of 10,000 OCR-scanned PDF documents](https://community.n8n.io/t/automated-n8n-workflow-for-analyzing-renaming-and-ai-assisted-processing-of-10-000-ocr-scanned-pdf-documents/132444)

<div class="topic-metadata">

**Author:** [@Chrystian\_Nowak](https://community.n8n.io/u/Chrystian_Nowak)\
**Replies:** 5\
**Last updated:** [September 1, 2025, 2:12pm UTC](https://community.n8n.io/t/automated-n8n-workflow-for-analyzing-renaming-and-ai-assisted-processing-of-10-000-ocr-scanned-pdf-documents/132444 "2025-09-01T14:12:23Z")

</div>

Hello dear n8n community, I’m reaching out for support in building a comprehensive workflow using n8n to process around 10,000 locally stored PDF documents. All of these files have been scanned and OCR-processed using N…

---

## [Input pdf that contain image in ai agent](https://community.n8n.io/t/input-pdf-that-contain-image-in-ai-agent/166251)

<div class="topic-metadata">

**Author:** [@Futurebillionaire](https://community.n8n.io/u/Futurebillionaire)\
**Replies:** 4\
**Last updated:** [August 13, 2025, 7:03pm UTC](https://community.n8n.io/t/input-pdf-that-contain-image-in-ai-agent/166251 "2025-08-13T19:03:27Z")

</div>

i need to input pdf that contain image in ai agent Describe the problem/error/question i need to input pdf that contain image in ai agent, i dont know how What is the error message (if any)? Please share your workflow (…

---

## [Need help with generating google slides](https://community.n8n.io/t/need-help-with-generating-google-slides/165220)

<div class="topic-metadata">

**Author:** [@you229ssef](https://community.n8n.io/u/you229ssef)\
**Replies:** 2\
**Last updated:** [August 12, 2025, 9:27am UTC](https://community.n8n.io/t/need-help-with-generating-google-slides/165220 "2025-08-12T09:27:29Z")

</div>

hey so long story short i wanted to make a workflow where if it gets a pdf file from telegram it will extract everything from it and sent it to the AI agent to use that file as a guide to make a google slide presentation…

---

## [Http request to stirlingpdf doesn't work with some pdfs](https://community.n8n.io/t/http-request-to-stirlingpdf-doesnt-work-with-some-pdfs/163606)

<div class="topic-metadata">

**Author:** [@jon123](https://community.n8n.io/u/jon123)\
**Replies:** 0\
**Last updated:** [August 7, 2025, 3:46am UTC](https://community.n8n.io/t/http-request-to-stirlingpdf-doesnt-work-with-some-pdfs/163606 "2025-08-07T03:46:04Z")

</div>

I had discussed this with the StirlingPDF dev here: Some PDF's PDF-to-Img but others fail · Stirling-Tools/Stirling-PDF · Discussion #2784 · GitHub We couldn’t quite get to the bottom of it. Basically, when n8n sends a…

---

## [Best way to ingest and vectorize PDFs](https://community.n8n.io/t/best-way-to-ingest-and-vectorize-pdfs/156163)

<div class="topic-metadata">

**Author:** [@Antoine101](https://community.n8n.io/u/Antoine101)\
**Replies:** 5\
**Last updated:** [July 29, 2025, 4:22pm UTC](https://community.n8n.io/t/best-way-to-ingest-and-vectorize-pdfs/156163 "2025-07-29T16:22:10Z")

</div>

Hi everyone, I am using n8n for the first time. I am creating a local RAG chat agent at my company to retrieve information from our internal knowledge base. I have deployed n8n locally through the self hosted starter k…

---

## [Extract Data from PDF](https://community.n8n.io/t/extract-data-from-pdf/154726)

<div class="topic-metadata">

**Author:** [@sasake](https://community.n8n.io/u/sasake)\
**Replies:** 5\
**Last updated:** [July 24, 2025, 4:47pm UTC](https://community.n8n.io/t/extract-data-from-pdf/154726 "2025-07-24T16:47:20Z")

</div>

Hi, I’m using n8n on local machine using dockers. I created a workflow to pick a pdf file from Google Drive and try to extract data using ‘Extract from File’. Unfortunately, when I look at the ‘Table’ tab, it turns out …

---

## [Getting "DOMMatrix is not defined" error in Extract from PDF node](https://community.n8n.io/t/getting-dommatrix-is-not-defined-error-in-extract-from-pdf-node/133880)

<div class="topic-metadata">

**Author:** [@Jules](https://community.n8n.io/u/Jules)\
**Replies:** 13\
**Last updated:** [July 2, 2025, 10:11am UTC](https://community.n8n.io/t/getting-dommatrix-is-not-defined-error-in-extract-from-pdf-node/133880 "2025-07-02T10:11:50Z")

</div>

Describe the problem/error/question Im using HTTP request node to get a PDF file and then using Extract from file node to extract the data from the PDF file. This was all working fine before, but now i’m getting a “DOMMa…

---

## [HTTP request makes .pdf to .html (slack attachment(](https://community.n8n.io/t/http-request-makes-pdf-to-html-slack-attachment/119571)

<div class="topic-metadata">

**Author:** [@krautpotato](https://community.n8n.io/u/krautpotato)\
**Replies:** 9\
**Last updated:** [June 11, 2025, 8:54am UTC](https://community.n8n.io/t/http-request-makes-pdf-to-html-slack-attachment/119571 "2025-06-11T08:54:14Z")

</div>

Hey there, build a flow to get invoices from a slack channel where we download the .pdfs with GET request. I can open the files manually and get the .pdf to download but n8n is only putting out a .html file.

---

## [PDF Scans \> TEXT in Default Data Loader (image pdf) processing](https://community.n8n.io/t/pdf-scans-text-in-default-data-loader-image-pdf-processing/111030)

<div class="topic-metadata">

**Author:** [@buildscool](https://community.n8n.io/u/buildscool)\
**Replies:** 6\
**Last updated:** [May 22, 2025, 5:06pm UTC](https://community.n8n.io/t/pdf-scans-text-in-default-data-loader-image-pdf-processing/111030 "2025-05-22T17:06:46Z")

</div>

Hi everyone, I am building a robust agent for loading data from GDRIVE → Vector storage. Right now I am working on having it handle .PDFs. It loops through text PDFs fine, but seems to get stuck at PDF scans that are i…

---

## [Requirement out of large PDF files](https://community.n8n.io/t/requirement-out-of-large-pdf-files/111612)

<div class="topic-metadata">

**Author:** [@Jop\_Van\_de\_Wiel](https://community.n8n.io/u/Jop_Van_de_Wiel)\
**Replies:** 7\
**Last updated:** [May 8, 2025, 9:09am UTC](https://community.n8n.io/t/requirement-out-of-large-pdf-files/111612 "2025-05-08T09:09:02Z")

</div>

Can someone help me out? I am looking for an efficient method to extract all building requirements from a legal contract. This appears to be possible using ChatGPT-4. The challenge, however, lies in the fact that these …

---

## [Convert large XML to PDF using standard n8n nodes](https://community.n8n.io/t/convert-large-xml-to-pdf-using-standard-n8n-nodes/110245)

<div class="topic-metadata">

**Author:** [@andrew.m\_Leeloo](https://community.n8n.io/u/andrew.m_Leeloo)\
**Replies:** 0\
**Last updated:** [May 3, 2025, 1:47pm UTC](https://community.n8n.io/t/convert-large-xml-to-pdf-using-standard-n8n-nodes/110245 "2025-05-03T13:47:25Z")

</div>

Hi n8n Community, I’m working on a workflow where I need to: Receive an XML file via an HTTP request or from a public URL (like GitHub). Transform that XML into an HTML or structured format. Feed that content into an …

[Next page](https://community.n8n.io/tag/read-pdf/182.md?match_all_tags=true&page=1&tags%5B%5D=read-pdf)
