langchain-paddleocr

This package provides access to PaddleOCR's capabilities within the LangChain ecosystem.

Quick Install

pip install langchain-paddleocr

Basic Usage

PaddleOCRVLLoader

The PaddleOCRVLLoader enables you to:

• Extract text and layout information from PDF and image files using models from Baidu's PaddleOCR-VL series (e.g., PaddleOCR-VL, PaddleOCR-VL-1.5, PaddleOCR-VL-1.6)
• Process documents from local files or remote URLs

Basic usage of PaddleOCRVLLoader looks as follows:

from langchain_paddleocr import PaddleOCRVLLoader
from pydantic import SecretStr

loader = PaddleOCRVLLoader(
    file_path="path/to/document.pdf",
    base_url="your-api-endpoint",
    model="PaddleOCR-VL-1.5",
    access_token=SecretStr("your-access-token")  # Optional if using environment variable `PADDLEOCR_ACCESS_TOKEN`
)

docs = loader.load()

for doc in docs[:2]:
    print(f"Content: {doc.page_content[:200]}...")
    print(f"Source: {doc.metadata['source']}")
    print("---")

📖 Documentation

For full documentation, see the LangChain Docs.