OpenDataLoader PDF 集成

使用 LangChain Python 集成 OpenDataLoader PDF 文档加载器。

PDF Parsing for RAG: Convert to Markdown & JSON, Fast, Local, No GPU

OpenDataLoader PDF converts PDFs into LLM-ready Markdown and JSON with accurate reading order, table extraction, and bounding boxes—all running locally on your machine.

Why developers choose OpenDataLoader:

• Deterministic—Same input always produces same output (no LLM hallucinations)
• Fast—Process 100+ pages per second on CPU
• Private—100% local, zero data transmission
• Accurate—Bounding boxes for every element, correct multi-column reading order

概述

集成详情

Class	Package	Local	Serializable	JS support
OpenDataLoader PDF	langchain-opendataloader-pdf	✅	❌	❌

加载器特性

Source	Document Lazy Loading	Native Async Support
OpenDataLoaderPDFLoader	✅	❌

The OpenDataLoaderPDFLoader component enables you to parse PDFs into structured Document objects.

Requirements

• Python >= 3.10
• Java 11 or newer available on the system PATH

安装

pip install -U langchain-opendataloader-pdf

Quick start

from langchain_opendataloader_pdf import OpenDataLoaderPDFLoader

loader = OpenDataLoaderPDFLoader(
    file_path=["path/to/document.pdf", "path/to/folder"],
    format="text"
)
documents = loader.load()

for doc in documents:
    print(doc.metadata, doc.page_content[:80])

Parameters

Parameter	Type	Default	Description
file_path	str | List[str]	—	(Required) PDF file path(s) or directories
format	str	"text"	Output format: "text", "markdown", "json", "html"
split_pages	bool	True	Split into separate Documents per page
quiet	bool	False	Suppress console logging
password	str	None	Password for encrypted PDFs
use_struct_tree	bool	False	Use PDF structure tree (tagged PDFs)
table_method	str	"default"	"default" (border-based) or "cluster" (border + clustering)
reading_order	str	"xycut"	"xycut" or "off"
keep_line_breaks	bool	False	Preserve original line breaks
image_output	str	"off"	"off", "embedded" (Base64), or "external"
image_format	str	"png"	"png" or "jpeg"
content_safety_off	List[str]	None	Disable safety filters: "hidden-text", "off-page", "tiny", "hidden-ocg", "all"
replace_invalid_chars	str	None	Replacement for invalid characters

Usage examples

Output formats

# Plain text (default) - best for simple RAG
loader = OpenDataLoaderPDFLoader(file_path="doc.pdf", format="text")

# Markdown - preserves headings, lists, tables
loader = OpenDataLoaderPDFLoader(file_path="doc.pdf", format="markdown")

# JSON - structured data with bounding boxes
loader = OpenDataLoaderPDFLoader(file_path="doc.pdf", format="json")

# HTML - styled output
loader = OpenDataLoaderPDFLoader(file_path="doc.pdf", format="html")

Tagged PDF support

For accessible PDFs with structure tags (common in government/legal documents):

loader = OpenDataLoaderPDFLoader(
    file_path="accessible_document.pdf",
    use_struct_tree=True  # Use native PDF structure
)

Password-Protected PDFs

loader = OpenDataLoaderPDFLoader(
    file_path="encrypted.pdf",
    password="secret123"
)

Image handling

# Images are excluded by default (image_output="off")
# This is optimal for text-based RAG pipelines

# Embed images as Base64 (for multimodal RAG)
loader = OpenDataLoaderPDFLoader(
    file_path="doc.pdf",
    format="markdown",
    image_output="embedded",
    image_format="jpeg"  # or "png"
)

Document metadata

Each returned Document includes metadata:

doc.metadata
# {'source': 'document.pdf', 'format': 'text', 'page': 1}

Additional resources

• LangChain OpenDataLoader PDF integration GitHub
• LangChain OpenDataLoader PDF integration PyPI package
• OpenDataLoader PDF GitHub
• OpenDataLoader PDF Homepage

---

通过 MCP 将这些文档连接到 Claude、VSCode 等工具以获取实时答案。

在 GitHub 上编辑此页面 或 提交 issue。