Prepare PDF data for AI
OpenDataLoader PDF is an open source PDF parser that makes data available for artificial intelligence models. This Java-based project speeds up data processing processes by automating the accessibility of PDF documents.
Updates
- November 6, 2026: Stars 30,164 → 30,180, latest release v2.5.20 (November 6, 2026).
- November 4, 2026: Stars 30,129 → 30,164, latest release v2.5.18 (November 4, 2026).
- October 31, 2026: Stars 30,057 → 30,129, latest release v2.5.17 (October 30, 2026).
- October 27, 2026: Stars 29,817 → 30,057, latest release v2.5.16 (October 27, 2026).
What you get
- Converts PDF files to Markdown, JSON or HTML format for AI models.
- Provides high-accuracy data extraction for scanned documents and complex tables.
- Automatically tags PDF files in accordance with accessibility standards.
Installation
pip install -U opendataloader-pdfpip install -U "opendataloader-pdf[hybrid]"Running it
import opendataloader_pdf
# Batch all files in one call — each convert() spawns a JVM process, so repeated calls are slow
opendataloader_pdf.convert(
input_path=["file1.pdf", "file2.pdf", "folder/"],
output_dir="output/",
format="markdown,json"
)If you don't write code
I want to analyze the PDF files I have using the OpenDataLoader PDF tool and convert them into structured data formats (Markdown or JSON) that I can use in RAG or LLM processes. Can you help me create a script to run on my local computer using the Python SDK that will extract tables, headings, and text from my documents in the correct reading order? Also explain step by step how to enable hybrid mode for complex pages and customize the output.
Repository: https://github.com/opendataloader-project/opendataloader-pdf. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-04: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.