What is the Document Layout Graph extractor used for?

Archival documents, scanned PDFs, forms processing, structured extraction, document understanding.

When should I not use Document Layout Graph?

Simple text extraction (use text_extractor), images (use image_extractor). Reach for it when you need document understanding, layout-aware RAG, table/form extraction, and structured PDF parsing.

How much does the Document Layout Graph extractor cost?

5 cr/page, 20 cr/extraction. Credits are billed per unit processed; see mixpeek.com/pricing for the credit rate.

What file types does Document Layout Graph support?

PDF. It produces embeddings from intfloat__multilingual_e5_large_instruct.

Document

Document Graph Extractor

Name: Document Graph Extractor
Price: 25 USD
Author: Mixpeek

Decompose PDFs into spatial blocks (paragraphs, tables, forms, headers) with layout classification and E5 text embeddings.

v1 · 5 cr/page, 20 cr/extraction

Read Docs

Integrate Now

View on GitHub

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

Text Input string

Enter the text you want to process

Output

{
  "page_number": "Page number in original PDF (1-indexed)",
  "object_type": "Classified type of this block. PARAGRAPH: Regular text. TABLE: Tabular data. FORM: Form fields. LIST: Bulleted/numbered lists. HEADER/FOOTER: Page headers/footers. FIGURE: Images/diagrams. HANDWRITTEN: Handwritten content.",
  "block_index": "Block index within the page (0-indexed)",
  "bbox": "Bounding box coordinates for this block on the page",
  "text_raw": "Original extracted text from the block (before cleaning)",
  "text_corrected": "Cleaned and/or VLM-corrected text. Contains cleaned text for high-confidence blocks, VLM-corrected text for low-confidence blocks (if enabled).",
  "overall_confidence": "Extraction confidence score (0.0-1.0)",
  "confidence_tag": "Confidence category. A: >=0.85 (high). B: >=0.70 (medium). C: >=0.50 (low, may need verification). D: <0.50 (very low, needs VLM).",
  "document_graph_extractor_v1_text_embedding": "Dense vector embedding for text content (1024-dim E5)",
  "thumbnail_url": "URL to full page thumbnail (low-res image of entire page)",
  "segment_thumbnail_url": "URL to segment thumbnail (cropped to block's bounding box)",
  "total_pages": "Total pages in source PDF",
  "source_file": "Original source file name"
}

Ready to run Document Graph Extractor on your data? Spin it up in Studio: no infra to host.

Run this in Studio

Document Graph Extractor: common questions

What is the Document Layout Graph extractor used for?: Archival documents, scanned PDFs, forms processing, structured extraction, document understanding.
When should I not use Document Layout Graph?: Simple text extraction (use text_extractor), images (use image_extractor). Reach for it when you need document understanding, layout-aware RAG, table/form extraction, and structured PDF parsing.
How much does the Document Layout Graph extractor cost?: 5 cr/page, 20 cr/extraction. Credits are billed per unit processed; see mixpeek.com/pricing for the credit rate.
What file types does Document Layout Graph support?: PDF. It produces embeddings from intfloat__multilingual_e5_large_instruct.

Already have embeddings? Skip extraction: search your own vectors with MVS, from $25/mo for up to 1M vectors.

Try MVS →