Skip to main content

Docling

Langflow integrates with Docling through a bundle of components for parsing documents.

Install Docling dependency

important

You must install the Docling dependency to use the Docling components in Langflow.

Install the Docling extra in Langflow OSS with uv pip install 'langflow[docling]'.

Use Docling components in a flow

tip

To learn more about content extraction with Docling, see the video tutorial Docling + Langflow: Document Processing for AI Workflows.

This example demonstrates how to use Docling components to split a PDF in a flow:

  1. Connect a Docling and an Export DoclingDocument component to a Split Text component.

    The Docling component loads the document, and the Export DoclingDocument component converts the DoclingDocument into the format you select. This example converts the document to Markdown, with images represented as placeholders. The Split Text component will split the Markdown into chunks for the vector database to store in the next part of the flow.

  2. Connect a Chroma DB vector store component to the Split Text component's Chunks output.

  3. Connect an Embedding Model component to the Chroma DB component's Embedding port and a Chat Output component to view the extracted DataFrame.

  4. Add your OpenAI API key to the Embedding Model component.

    Docling and ExportDoclingDocument extracting and splitting text to vector database

  5. Add a file to the Docling component.

  6. To run the flow, click Playground.

    The chunked document is loaded as vectors into your vector database.

Docling components

The following sections describe the purpose and configuration options for each component in the Docling bundle.

Docling language model

The Docling language model component ingest documents, and then uses Docling to process them by running the Docling models locally.

It outputs files, which is the processed files with DoclingDocument data.

Docling parameters

NameTypeDescription
filesFileThe files to process.
pipelineStringDocling pipeline to use (standard, vlm).
ocr_engineStringOCR engine to use (easyocr, tesserocr, rapidocr, ocrmac).

Docling Serve

The Docling Serve component ingests documents, and then uses Docling to process them by connecting to your instance of Docling Serve.

It outputs files, which is the processed files with DoclingDocument data.

Docling Serve parameters

NameTypeDescription
filesFileThe files to process.
api_urlStringURL of the Docling Serve instance.
max_concurrencyIntegerMaximum number of concurrent requests for the server.
max_poll_timeoutFloatMaximum waiting time for the document conversion to complete.
api_headersDictOptional dictionary of additional headers required for connecting to Docling Serve.
docling_serve_optsDictOptional dictionary of additional options for Docling Serve.

Chunk DoclingDocument

The Chunk DoclingDocument component uses the DoclingDocument chunkers to split a document into chunks.

It outputs the chunked documents as a DataFrame.

Chunk DoclingDocument parameters

NameTypeDescription
data_inputsData/DataFrameThe data with documents to split in chunks.
chunkerStringWhich chunker to use (HybridChunker, HierarchicalChunker).
providerStringWhich tokenizer provider (Hugging Face, OpenAI).
hf_model_nameStringModel name of the tokenizer to use with the HybridChunker when Hugging Face is chosen.
openai_model_nameStringModel name of the tokenizer to use with the HybridChunker when OpenAI is chosen.
max_tokensIntegerMaximum number of tokens for the HybridChunker.
doc_keyStringThe key to use for the DoclingDocument column.

Export DoclingDocument

The Export DoclingDocument component exports DoclingDocument to Markdown, HTML, and other formats.

It can output the exported data as either Data or DataFrame.

Export DoclingDocument parameters

NameTypeDescription
data_inputsData/DataFrameThe data with documents to export.
export_formatStringSelect the export format to convert the input (Markdown, HTML, Plaintext, DocTags).
image_modeStringSpecify how images are exported in the output (placeholder, embedded).
md_image_placeholderStringSpecify the image placeholder for markdown exports.
md_page_break_placeholderStringAdd this placeholder between pages in the markdown output.
doc_keyStringThe key to use for the DoclingDocument column.
Search