PaddleOCR-VL

pip install langchain-paddleocr

from langchain_paddleocr import PaddleOCRVLLoader
from pydantic import SecretStr

loader = PaddleOCRVLLoader(
    file_path="path/to/document.pdf",
    api_url="your-api-endpoint",
    access_token=SecretStr("your-access-token")  # Optional if using environment variable
)

export PADDLEOCR_ACCESS_TOKEN="your-access-token"

loader = PaddleOCRVLLoader(
    file_path="path/to/document.pdf",
    api_url="your-api-endpoint"
)

loader = PaddleOCRVLLoader(
    file_path=["document1.pdf", "document2.jpg"],  # Multiple files
    api_url="your-api-endpoint",

    access_token=None,  # Optional: SecretStr for API authentication
    file_type="pdf",  # Optional: "pdf" or "image", or None for auto-detection

    use_doc_orientation_classify=False,  # Enable document orientation classification
    use_doc_unwarping=False,  # Enable document unwarping
    use_layout_detection=None,  # Enable layout detection (None = use service default)
    use_chart_recognition=None,  # Enable chart recognition (None = use service default)
    use_seal_recognition=None,  # Enable seal recognition (None = use service default)
    use_ocr_for_image_block=None,  # Run OCR on image blocks (None = use service default)

    layout_threshold=None,  # Detection threshold (None = use service default)
    layout_nms=None,  # Apply non-maximum suppression (None = use service default)
    layout_unclip_ratio=None,  # Layout unclip ratio (None = use service default)
    layout_merge_bboxes_mode=None,  # Mode for merging layout bounding boxes (None = use service default)
    layout_shape_mode=None,  # Layout shape mode (None = use service default)

    prompt_label=None,  # Prompt label for VLM (None = use service default)
    format_block_content=None,  # Format block content (None = use service default)
    repetition_penalty=None,  # Repetition penalty for VLM sampling (None = use service default)
    temperature=None,  # Temperature for VLM sampling (None = use service default)
    top_p=None,  # Top-p sampling value for VLM (None = use service default)
    min_pixels=None,  # Minimum pixels allowed in preprocessing (None = use service default)
    max_pixels=None,  # Maximum pixels allowed in preprocessing (None = use service default)
    max_new_tokens=None,  # Maximum tokens generated by VLM (None = use service default)

    merge_layout_blocks=None,  # Merge layout blocks across columns (None = use service default)
    markdown_ignore_labels=None,  # Layout labels to ignore in Markdown (None = use service default)
    vlm_extra_args=None,  # Additional VLM configuration parameters (None = use service default)

    prettify_markdown=None,  # Prettify Markdown output (None = use service default)
    show_formula_number=None,  # Include formula numbers in Markdown (None = use service default)
    restructure_pages=None,  # Restructure results across pages (None = use service default)
    merge_tables=None,  # Merge tables across pages (None = use service default)
    relevel_titles=None,  # Relevel titles (None = use service default)
    visualize=None,  # Include visualization results (None = use service default)

    additional_params=None,  # Additional API parameters
    timeout=300,  # Request timeout in seconds
)

# Load a single document
loader = PaddleOCRVLLoader(
    file_path="https://arxiv.org/pdf/2408.09869",
    api_url="your-api-endpoint"
)
docs = loader.load()

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

# Mixed file types - auto-detected
files = [
    "document.pdf",      # PDF file
    "image.jpg",         # Image file
    "https://example.com/report.pdf"  # Remote PDF
]

loader = PaddleOCRVLLoader(file_path=files, api_url="your-api-endpoint")

docs = loader.load()
first_doc = docs[0]

# Access raw API response for advanced processing
raw_response = first_doc.metadata["paddleocr_vl_raw_response"]
print(f"Layout results: {len(raw_response['result']['layoutParsingResults'])}")

try:
    docs = loader.load()
except ValueError as e:
    print(f"Processing failed: {e}")
    # Common issues: invalid API endpoint, authentication errors, unsupported file types

docs = loader.load()
if docs:
    raw_response = docs[0].metadata.get("paddleocr_vl_raw_response")
    print("API Response structure:", raw_response.keys())