import torch
from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer
from qwen_vl_utils import process_vision_info
from dots_ocr.utils import dict_promptmode_to_prompt
import math
from PIL import Image
from io import BytesIO
import requests

MIN_PIXELS = 3136
MAX_PIXELS = 11289600
IMAGE_FACTOR = 28

model_path = "thangtv27/dots_ocr_finetuned"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    attn_implementation="flash_attention_2",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
).to("cuda")
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

prompt = """Please output the layout information from the PDF image, including each layout element's bbox, its category, and the corresponding text content within the bbox.

1. Bbox format: [x1, y1, x2, y2]

2. Layout Categories: The possible categories are ['Caption', 'Footnote', 'Formula', 'List-item', 'Page-footer', 'Page-header', 'Picture', 'Section-header', 'Table', 'Text', 'Title'].

3. Text Extraction & Formatting Rules:
    - Picture: For the 'Picture' category, the text field should be omitted.
    - Formula: Format its text as LaTeX.
    - Table: Format its text as HTML. 
    - All Others (Text, Title, etc.): Format their text as Markdown.

4. Constraints:
    - The output text must be the original text from the image, with no translation.
    - All layout elements must be sorted according to human reading order.

5. Final Output: The entire output must be a single JSON object.
"""

image = "test.jpg"

messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image
                },
                {"type": "text", "text": prompt}
            ]
        }
    ]

# Preparation for inference
text = processor.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True
)

image_inputs, video_inputs = process_vision_info(messages)

inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)

inputs = inputs.to("cuda")
model.eval()

generated_ids = model.generate(**inputs, repetition_penalty=1.15, max_new_tokens=5000)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)