OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

oxidize-pdf

oxidize-pdf is an open-source Rust library for generating, parsing, modifying, extracting and validating PDFs, with structure-aware chunking for AI and RAG document processing.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

oxidize-pdf — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Rust application needs PDF parsing or broader PDF operations, particularly when an AI or RAG pipeline benefits from chunks that retain document structure and source-page context.

Who it is for

  • Rust developers adding PDF extraction or manipulation to an application.
  • Teams building document-ingestion and RAG pipelines that need structured PDF chunks before embedding or retrieval.

Documented uses

  • Extract text and structural metadata from PDFs.
  • Prepare PDF content as chunks with page, heading, element and token information for downstream retrieval workflows.
  • Generate, modify, combine or validate PDFs within a Rust application.
Before you choose

Requirements & limits

The repository identifies the project as open source under the MIT license.

  • The library prepares content for downstream AI workflows but does not include built-in machine learning or generate embeddings.
  • Chunk output can carry page numbers, bounding boxes, element types, heading context and token estimates.
  • JSON serialization of chunks requires the semantic feature.
  • PDF rasterization is not included and requires a separate renderer.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Extract structure-aware chunks from a PDF

Use the library's parser to produce PDF chunks with contextual metadata for downstream processing.

Before you start

  • Rust 1.88 or later
  • The oxidize-pdf crate
  • A PDF file to process

Steps

  1. Add oxidize-pdf = "5.4.2" to the Rust project's dependencies.

  2. Open the file with PdfDocument::open("document.pdf")?.

  3. Call doc.rag_chunks()? to obtain the chunks.

  4. Use fields such as full_text, page_numbers, element_types, heading_context and token_estimate in the next processing stage.

Expected outcome

A collection of PDF chunks with text and structure-related metadata, ready for application-specific downstream processing.

Guide limitations

  • The library does not include a built-in machine-learning component or perform embedding generation.
  • Page rasterization is not provided; bitmap output requires a separate renderer.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
bzsanti/oxidizePdf · Official homepage title · retained in its source language
How we review sourcesSuggest a correction