docling/docs/examples/vlm_pipeline_api_model.py

import logging
import os
from pathlib import Path

import requests
from dotenv import load_dotenv

from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
    VlmPipelineOptions,
)
from docling.datamodel.pipeline_options_vlm_model import ApiVlmOptions, ResponseFormat
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline


def ollama_vlm_options(model: str, prompt: str):
    options = ApiVlmOptions(
        url="http://localhost:11434/v1/chat/completions",  # the default Ollama endpoint
        params=dict(
            model=model,
        ),
        prompt=prompt,
        timeout=90,
        scale=1.0,
        response_format=ResponseFormat.MARKDOWN,
    )
    return options


def watsonx_vlm_options(model: str, prompt: str):
    load_dotenv()
    api_key = os.environ.get("WX_API_KEY")
    project_id = os.environ.get("WX_PROJECT_ID")

    def _get_iam_access_token(api_key: str) -> str:
        res = requests.post(
            url="https://iam.cloud.ibm.com/identity/token",
            headers={
                "Content-Type": "application/x-www-form-urlencoded",
            },
            data=f"grant_type=urn:ibm:params:oauth:grant-type:apikey&apikey={api_key}",
        )
        res.raise_for_status()
        api_out = res.json()
        print(f"{api_out=}")
        return api_out["access_token"]

    options = ApiVlmOptions(
        url="https://us-south.ml.cloud.ibm.com/ml/v1/text/chat?version=2023-05-29",
        params=dict(
            model_id=model,
            project_id=project_id,
            parameters=dict(
                max_new_tokens=400,
            ),
        ),
        headers={
            "Authorization": "Bearer " + _get_iam_access_token(api_key=api_key),
        },
        prompt=prompt,
        timeout=60,
        response_format=ResponseFormat.MARKDOWN,
    )
    return options


def main():
    logging.basicConfig(level=logging.INFO)

    # input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
    input_doc_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf")

    pipeline_options = VlmPipelineOptions(
        enable_remote_services=True  # <-- this is required!
    )

    # The ApiVlmOptions() allows to interface with APIs supporting
    # the multi-modal chat interface. Here follow a few example on how to configure those.

    # One possibility is self-hosting model, e.g. via Ollama.
    # Example using the Granite Vision  model: (uncomment the following lines)
    pipeline_options.vlm_options = ollama_vlm_options(
        model="granite3.2-vision:2b",
        prompt="OCR the full page to markdown.",
    )

    # Another possibility is using online services, e.g. watsonx.ai.
    # Using requires setting the env variables WX_API_KEY and WX_PROJECT_ID.
    # Uncomment the following line for this option:
    # pipeline_options.vlm_options = watsonx_vlm_options(
    #     model="ibm/granite-vision-3-2-2b", prompt="OCR the full page to markdown."
    # )

    # Create the DocumentConverter and launch the conversion.
    doc_converter = DocumentConverter(
        format_options={
            InputFormat.PDF: PdfFormatOption(
                pipeline_options=pipeline_options,
                pipeline_cls=VlmPipeline,
            )
        }
    )
    result = doc_converter.convert(input_doc_path)
    print(result.document.export_to_markdown())


if __name__ == "__main__":
    main()