Blog post: https://sawin.com.np/blog/sarvam-vision-nepali-ocr

extract_devanagari_text.py

from sarvamai import SarvamAI
from PyPDF2 import PdfReader, PdfWriter
import os


def split_pdf(input_path, output_dir, chunk_size=10):
    reader = PdfReader(input_path)
    total_pages = len(reader.pages)

    os.makedirs(output_dir, exist_ok=True)

    file_paths = []

    for start in range(0, total_pages, chunk_size):
        writer = PdfWriter()
        end = min(start + chunk_size, total_pages)

        for i in range(start, end):
            writer.add_page(reader.pages[i])

        output_path = os.path.join(output_dir, f"chunk_{start+1}_to_{end}.pdf")

        with open(output_path, "wb") as f:
            writer.write(f)

        file_paths.append(output_path)

    return file_paths


client = SarvamAI(api_subscription_key="your-api-token")


chunks = split_pdf("/path/to/document.pdf", "chunks")


for i, chunk in enumerate(chunks):
    job = client.document_intelligence.create_job(
        language="ne-IN",
        output_format="md"
    )
    print(f"Job created: {job.job_id}")

    job.upload_file(chunk)
    print(f"File uploaded: {chunk}")

    job.start()
    print("Job started")

    status = job.wait_until_complete()
    print(f"Job completed with state: {status.job_state}")

    metrics = job.get_page_metrics()
    print(f"Page metrics: {metrics}")

    job.download_output("./output.zip")
    os.rename("./output.zip", f"./output_{i}.zip")
    print(f"Output saved to ./output_{i}.zip")