LightOnOCR-0.9B-16k-1025

uv venv --python 3.12 --seed
source .venv/bin/activate

# install any version higher than 0.11.1
uv pip install vllm==0.11.2
# extra deps need only to run the example below
uv pip install pypdfium2 pillow requests

vllm serve lightonai/LightOnOCR-0.9B-16k-1025 \
    --limit-mm-per-prompt '{"image": 1}'

import base64
import requests
import pypdfium2 as pdfium
import io

ENDPOINT = "http://localhost:8000/v1/chat/completions"
MODEL = "lightonai/LightOnOCR-0.9B-16k-1025"

# Download PDF from arXiv
pdf_url = "https://arxiv.org/pdf/2412.13663"
pdf_data = requests.get(pdf_url).content

# Open PDF and convert first page to image
pdf = pdfium.PdfDocument(pdf_data)
page = pdf[0]
# Render at 200 DPI (scale factor = 200/72 ≈ 2.77)
pil_image = page.render(scale=2.77).to_pil()

# Convert to base64
buffer = io.BytesIO()
pil_image.save(buffer, format="PNG")
image_base64 = base64.b64encode(buffer.getvalue()).decode('utf-8')

# Make request
payload = {
    "model": MODEL,
    "messages": [{
        "role": "user",
        "content": [{
            "type": "image_url",
            "image_url": {"url": f"data:image/png;base64,{image_base64}"}
        }]
    }],
    "max_tokens": 4096,
    "temperature": 0.2,
    "top_p": 0.9,
}

response = requests.post(ENDPOINT, json=payload)
text = response.json()['choices'][0]['message']['content']
print(text)