Nanonets-OCR2：一款可将文档转换为结构化markdown的模型，具备智能内容识别与语义标注功能

from PIL import Image
from transformers import AutoTokenizer, AutoProcessor, AutoModelForImageTextToText

model_path = "nanonets/Nanonets-OCR2-3B"

model = AutoModelForImageTextToText.from_pretrained(
    model_path, 
    torch_dtype="auto", 
    device_map="auto", 
    attn_implementation="flash_attention_2"
)
model.eval()

tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = AutoProcessor.from_pretrained(model_path)


def ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=4096):
    prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and ☑ for check boxes."""
    image = Image.open(image_path)
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": [
            {"type": "image", "image": f"file://{image_path}"},
            {"type": "text", "text": prompt},
        ]},
    ]
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt")
    inputs = inputs.to(model.device)
    
    output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False)
    generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
    
    output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    return output_text[0]

image_path = "/path/to/your/document.jpg"
result = ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=15000)
print(result)

vllm serve nanonets/Nanonets-OCR2-3B

from openai import OpenAI
import base64

client = OpenAI(api_key="123", base_url="http://localhost:8000/v1")

model = "nanonets/Nanonets-OCR2-3B"

def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

def ocr_page_with_nanonets_s(img_base64):
    response = client.chat.completions.create(
        model=model,
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/png;base64,{img_base64}"},
                    },
                    {
                        "type": "text",
                        "text": "Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and ☑ for check boxes.",
                    },
                ],
            }
        ],
        temperature=0.0,
        max_tokens=15000
    )
    return response.choices[0].message.content

test_img_path = "/path/to/your/document.jpg"
img_base64 = encode_image(test_img_path)
print(ocr_page_with_nanonets_s(img_base64))

import requests

url = "https://extraction-api.nanonets.com/extract"
headers = {"Authorization": <API KEY>}

files = {"file": open("/path/to/your/file", "rb")}
data = {"output_type": "markdown"}
data["model"] = "nanonets"

response = requests.post(url, headers=headers, files=files, data=data)
print(response.json())

user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and ☑ for check boxes."""

import requests

url = "https://extraction-api.nanonets.com/extract"
headers = {"Authorization": <API KEY>}

files = {"file": open("/path/to/your/file", "rb")}
data = {"output_type": "markdown-financial-docs"}

response = requests.post(url, headers=headers, files=files, data=data)
print(response.json())

@misc{Nanonets-OCR2,
  title={Nanonets-OCR2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging},
  author={Souvik Mandal and Ashish Talewar and Siddhant Thakuria and Paras Ahuja and Prathamesh Juvatkar},
  year={2025},
}