Ctrlk
Login
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Setting up Docling in n8n

Introduction

Docling is an advanced document parsing engine designed to convert complex, multi-format documents (such as PDFs, DOCX, and PPTX) into clean, LLM-ready Markdown or JSON structures. Integrating Docling into your n8n workflows within the GLBNXT ecosystem allows you to build highly accurate Retrieval-Augmented Generation (RAG) pipelines and document processing agents.

Prerequisites

Before configuring Docling within your n8n workflows, ensure you have the following:

  • n8n Environment: An active instance of n8n running within your secure GLBNXT workspace.

  • Docling Credentials: Use the url provided in Configuration to setup your Docling Account.

Installation

Step 1: Add the Docling Serve Node

  1. Create a new workflow or open an existing one

  2. Open the nodes panel by selecting + or pressing N

  3. Search for Docling Serve

  1. Select one of the Actions

Step 2: Add the Credentials

  1. Create a new Docling Account

  2. Use this Base URL:

  1. You can leave the API Key open

  2. You are now able to use Docling in n8n

Step 3: Example

  1. Create the following flow in n8n:

  • Parser: Search for 'Parser' in the Search bar, drag the node to the playground and select 'Stringify' for Mode.

  • Chat Output: Search for 'Chat Output' in the Search bar and drag the node to the playground.

  1. Select a file in the Docling Serve node

  2. Click Playground at the right top corner of your screen

  3. Press Run Flow at the bottom of your screen

  4. You will get the following output:

  5. The json "text" output displays the converted content of the selected document and can be used to build highly effective document processing agents.

Configuration

This section covers all configuration options available in Docling. Use these parameters to customize extraction pipelines, adjust OCR models, tune table structure identification, and tweak Vision-Language Models (VLM).

1. Document Format & Export Configurations

Resource

  • Type: string (Dropdown selector)

  • Default: Document

  • Description: Specifies the overarching asset type being targeted for the processing workflow.

  • Useful Scenario: Primarily used to establish whether the incoming asset stream is a text/file asset versus other system resources.

Operation

  • Type: string (Dropdown selector)

  • Default: Convert From URL

  • Description: Defines the execution method applied to the resource.

  • Useful Scenario: Select Convert From URL when documents are hosted on external cloud storage (like AWS S3 or a public web server) to fetch and process them on the fly.

Source URL

  • Type: string (URL Input field)

  • Default: Empty / Example placeholder ([https://example.com/document.pdf](https://example.com/document.pdf))

  • Description: The direct network path where the target document is located for remote processing.

  • Useful Scenario: Point this directly to a shared corporate link or a cloud-hosted PDF file that needs to be imported into your system.

From Formats

  • Type: string (Dropdown selector / Multi-select)

  • Default: Select (All/Auto)

  • Description: Filters or explicitly defines the allowed incoming file formats for processing.

  • Useful Scenario: If you want to ensure your pipeline ignores accidental spreadsheet uploads and strictly handles legal briefs, you can restrict this option to source formats like PDF or Word.

To Formats

  • Type: string (Dropdown selector / Multi-select)

  • Default: Empty

  • Description: Specifies the desired target output format(s) for the converted document (e.g., Markdown, JSON, HTML).

  • Useful Scenario: Set this to Markdown if you are feeding the resulting text chunks straight into an LLM context window.

Image Export Mode

  • Type: string (Dropdown selector)

  • Default: Embedded

  • Description: Controls how extracted document images are packaged within the final export file.

  • Useful Scenario: Set to Embedded if you require an autonomous single-file asset containing base64 images. Use alternative referenced paths if you prefer keeping file sizes lean.

Images Scale

  • Type: number (Numeric input)

  • Default: 2

  • Description: Adjusts the scaling multiplier or resolution modifier applied to images extracted from the document body.

  • Useful Scenario: Increase the scaling value if you notice that embedded charts or handwritten notes require higher clarity for downstream human review or secondary inspection.

Include Images

  • Type: boolean (Toggle switch)

  • Default: true (Enabled)

  • Description: Determines whether visual images, figures, and graphical assets should be preserved and extracted alongside the text.

  • Useful Scenario: Turn this toggle off to speed up processing times and save storage if you only care about textual data extraction.

Markdown Page Break

  • Type: string (Text input field)

  • Default: Empty (<!-- page-break --> placeholder)

  • Description: Appends a specific string boundary token between individual pages within Markdown generation tracks.

  • Useful Scenario: Specifying a clear tag allows automated static site generators or page splitters downstream to isolate page-by-page rendering.

2. OCR (Optical Character Recognition) Controls

Do OCR

  • Type: boolean (Toggle switch)

  • Default: true (Enabled)

  • Description: Activates or deactivates OCR parsing on bitmap, scanned, or non-selectable visual documents.

  • Useful Scenario: Turn this off if you exclusively process raw digital-native text documents (like direct HTML or system-generated text files) to drastically decrease overall execution latency.

Force OCR

  • Type: boolean (Toggle switch)

  • Default: false (Disabled)

  • Description: Replaces a PDF file's native underlying text layer entirely with freshly synthesized characters computed directly via the active OCR engine.

  • Useful Scenario: Indispensable for handling legacy documents possessing corrupted or misaligned embedded text tracks where copy-pasted words manifest as gibberish.

OCR Engine

  • Type: string (Dropdown selector)

  • Default: Auto

  • Description: Selects the structural toolkit ecosystem deployed for running standard OCR extraction models.

  • Useful Scenario: Switch from Auto to a specific engine framework if your hosting environment implements a highly optimized local engine binary.

OCR Languages

  • Type: string (Comma-separated text input)

  • Default: Empty (en, de, fr placeholder)

  • Description: Feeds targeted explicit language code requirements down to the underlying active engine library instances.

  • Useful Scenario: Explicitly supply regional language tags when parsing complex multi-lingual trade contracts containing specific localized character accents.

3. Core Engine Pipelines & Table Management

PDF Backend

  • Type: string (Dropdown selector)

  • Default: Diparse V4 (Default)

  • Description: Adjusts the specific backend library framework engine targeted for decoding layout coordinates and structural features inside PDF binaries.

  • Useful Scenario: Swap backends if a highly specialized PDF formatting layout fails to map correctly under the default parser.

Do Table Structure

  • Type: boolean (Toggle switch)

  • Default: true (Enabled)

  • Description: Toggles whether advanced spatial structure extraction features should map grid blocks across document tables.

  • Useful Scenario: Turn this off when digitizing narrative-heavy text novels or basic text logs to skip intensive spatial positioning passes.

Table Cell Matching

  • Type: boolean (Toggle switch)

  • Default: true (Enabled)

  • Description: Ties visual engine bounding calculations directly back against low-level PDF structural layout lines.

  • Useful Scenario: Disabling this helps avoid table generation failures if a document contains heavily merged columns or complex internal borders that cause structural bounding boxes to break.

Table Mode

  • Type: string (Dropdown selector)

  • Default: Accurate (Default)

  • Description: Adjusts the structural layout identification weight models toward high-speed or deep-accuracy parsing algorithms.

  • Useful Scenario: Select a faster mode for rapid real-time screen indexing pipelines, or leave it on Accurate when transforming detailed multi-column financial reports.

Pipeline

  • Type: string (Dropdown selector)

  • Default: Standard (Default)

  • Description: Instructs the system which core processing assembly pipeline template path executes your ingestion.

  • Useful Scenario: Switch to specialized alternative pipelines if your specific document workflow requires custom model routing on intensive graphic structures.

4. Layout, Enrichments, & Vision-Language Models (VLM)

Enriched Data Extractors

  • Do Chart Extraction: Extracts and structures statistical or informational data charts into usable matrix values (false by default).

  • Do Code Enrichment: Extracts, identifies, and formats inline source code or script blocks (false by default).

  • Do Formula Enrichment: Evaluates complex mathematical structures and equations into rendered text or layout strings (false by default).

  • Useful Scenario: Highly effective if you build educational workflows converting scanned scientific papers or engineering textbooks into clean, web-ready markdown materials.

Image Descriptions and Classifications

  • Do Picture Classification: Automatically tags and catalogs the broad category type of pictures found within documents (false by default).

  • Do Picture Description: Generates context-aware textual AI descriptions for visual elements found in documents (false by default).

  • Picture Description Area Threshold: (Default: 0.05) Minimum graphic area page share size required before firing AI evaluation passes.

  • Useful Scenario: Enables accessibility compliance pipelines to auto-generate alt-text descriptions for charts inside corporate manuals.

VLM Custom Ensembles (Presets)

  • Code/Formula Preset: Text input field allowing a custom preset configuration or model selection to optimize code and mathematical formulas.

  • Picture Description Preset: Allows targeting a specific vision model variant optimized for generating text descriptions from images.

  • VLM Pipeline Preset: Connects your document structure engine instance with pre-configured Vision-Language Models.

  • Useful Scenario: Essential if your enterprise infrastructure mandates the pipeline to rely on highly specialized, fine-tuned, or offline VLM models.

5. System Execution Constraints

Document Timeout

  • Type: number (Numeric input field)

  • Default: 300 (seconds)

  • Description: Sets the maximum processing time allowed for a single document workflow before forcing a thread cancellation.

  • Useful Scenario: Lower this value in user-facing synchronous web applications to prevent corrupted or excessively massive files from hanging server worker threads.

Abort on Error

  • Type: boolean (Toggle switch)

  • Default: false (Disabled)

  • Description: Dictates whether the pipeline should immediately crash upon encountering an exception or log it and keep processing remaining pages.

  • Useful Scenario: Turn this toggle on during strict automated validation testing, or leave it disabled in bulk-production setups so a single corrupted layout segment doesn't ruin a large batch import.

6. Document Bounds Management

Page Range Start

  • Type: number (Numeric input field)

  • Default: 0 (Processes from the true start of the document)

  • Description: Sets the initial page boundary index where processing, layout rendering, and text conversion begin.

  • Useful Scenario: Set to a specific page number if you wish to skip introductory title pages, table of contents, or legal disclaimers.

Page Range End

  • Type: number (Numeric input field)

  • Default: 0 (Processes until the end of the document)

  • Description: Caps the maximum page bounds. A value of 0 processes the entire asset through its final page.

  • Useful Scenario: When parsing 500-page corporate financial filings but your analytics application only needs the introductory summary, set an ending bounds limit to save resources.

Troubleshooting

Issue: Timeout Errors on Large PDF Documents

  • Cause: Complex or multi-hundred-page PDFs can require significant processing time for layout and OCR analysis.

  • Solution: Increase the Timeout parameter within the n8n HTTP Request node settings (under Advanced Settings) to 300000 ms (5 minutes) or split massive document streams into smaller chunks prior to parsing.

Issue: Binary File Property Missing

  • Cause: The HTTP Request node is looking for a binary property that doesn't match the output name of the incoming source file.

  • Solution: Verify the input scheme. Check the execution data from the preceding node and match the property name exactly (e.g., attachment_0 vs data).

Issue: Network Isolation / Connection Refused

  • Cause: GLBNXT’s default strict security compliance policy blocks unauthorized traffic between containers.

  • Solution: Ensure that your n8n network policies explicitly allow outbound requests to the internal microservice endpoint hosting Docling.

Need help? Contact the GLBNXT support team or ask a GLBNXT agent to walk you through the setup.

PreviousSetting up PostgreSQL in n8nNextSetting up Docling in LangFlow

Last updated

Was this helpful?