Gemini OCR

Traceable Generative Markdown for PDFs

gemini-ocr provides anchorite provider plugins that convert PDFs to traceable Markdown using Google Cloud APIs.

• GeminiMarkdownProvider — generates Markdown via the Gemini API
• DocAIMarkdownProvider — generates Markdown via Document AI Layout
• DocAIAnchorProvider — extracts bounding boxes via Document AI OCR
• DoclingMarkdownProvider — generates Markdown via Docling (stub)

Quick Start

import asyncio
from pathlib import Path

import anchorite
from gemini_ocr import DocAIAnchorProvider, GeminiMarkdownProvider

async def main():
    markdown_provider = GeminiMarkdownProvider(
        project_id="my-gcp-project",
        location="us-central1",
        model_name="gemini-2.5-flash",
    )
    anchor_provider = DocAIAnchorProvider(
        project_id="my-gcp-project",
        location="us-central1",
        processor_id="projects/.../processors/...",
    )

    chunks = anchorite.document.chunks(Path("document.pdf"))
    result = await anchorite.process_document(
        chunks, markdown_provider, anchor_provider, renumber=True
    )

    print(result.markdown_content)
    print(result.annotate())   # Markdown with inline <span data-bbox="..."> tags

asyncio.run(main())

Configuration via Environment Variables

from_env() builds providers from environment variables, useful for twelve-factor deployments:

import anchorite
from gemini_ocr import from_env

markdown_provider, anchor_provider = from_env()
chunks = anchorite.document.chunks(Path("document.pdf"))
result = await anchorite.process_document(chunks, markdown_provider, anchor_provider)

License

This project is licensed under the MIT License - see the LICENSE file for details.