Smoldocling 256m Preview

# Prerequisites:
# pip install torch
# pip install docling_core
# pip install transformers

import torch
from docling_core.types.doc import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
from pathlib import Path

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

# Load images
image = load_image("https://upload.wikimedia.org/wikipedia/commons/7/76/GazettedeFrance.jpg")

# Initialize processor and model
processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview")
model = AutoModelForVision2Seq.from_pretrained(
    "ds4sd/SmolDocling-256M-preview",
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
).to(DEVICE)

# Create input messages
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Convert this page to docling."}
        ]
    },
]

# Prepare inputs
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = inputs.to(DEVICE)

# Generate outputs
generated_ids = model.generate(**inputs, max_new_tokens=8192)
prompt_length = inputs.input_ids.shape[1]
trimmed_generated_ids = generated_ids[:, prompt_length:]
doctags = processor.batch_decode(
    trimmed_generated_ids,
    skip_special_tokens=False,
)[0].lstrip()

# Populate document
doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
print(doctags)
# create a docling document
doc = DoclingDocument.load_from_doctags(doctags_doc, document_name="Document")

# export as any format
# HTML
# Path("Out/").mkdir(parents=True, exist_ok=True)
# output_path_html = Path("Out/") / "example.html"
# doc.save_as_html(output_path_html)
# MD
print(doc.export_to_markdown())

# Prerequisites:
# pip install vllm
# pip install docling_core
# place page images you want to convert into "img/" dir

import time
import os
from vllm import LLM, SamplingParams
from PIL import Image
from docling_core.types.doc import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument
from pathlib import Path

# Configuration
MODEL_PATH = "ds4sd/SmolDocling-256M-preview"
IMAGE_DIR = "img/"  # Place your page images here
OUTPUT_DIR = "out/"
PROMPT_TEXT = "Convert page to Docling."

# Ensure output directory exists
os.makedirs(OUTPUT_DIR, exist_ok=True)

# Initialize LLM
llm = LLM(model=MODEL_PATH, limit_mm_per_prompt={"image": 1})

sampling_params = SamplingParams(
    temperature=0.0,
    max_tokens=8192)

chat_template = f"<|im_start|>User:{PROMPT_TEXT}
Assistant:"

image_files = sorted([f for f in os.listdir(IMAGE_DIR) if f.lower().endswith((".png", ".jpg", ".jpeg"))])

start_time = time.time()
total_tokens = 0

for idx, img_file in enumerate(image_files, 1):
    img_path = os.path.join(IMAGE_DIR, img_file)
    image = Image.open(img_path).convert("RGB")

    llm_input = {"prompt": chat_template, "multi_modal_data": {"image": image}}
    output = llm.generate([llm_input], sampling_params=sampling_params)[0]
    
    doctags = output.outputs[0].text
    img_fn = os.path.splitext(img_file)[0]
    output_filename = img_fn + ".dt"
    output_path = os.path.join(OUTPUT_DIR, output_filename)

    with open(output_path, "w", encoding="utf-8") as f:
        f.write(doctags)

    # To convert to Docling Document, MD, HTML, etc.:
    doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
    doc = DoclingDocument.load_from_doctags(doctags_doc, document_name="Document")
    # export as any format
    # HTML
    # output_path_html = Path(OUTPUT_DIR) / f"{img_fn}.html"
    # doc.save_as_html(output_path_html)
    # MD
    output_path_md = Path(OUTPUT_DIR) / f"{img_fn}.md"
    doc.save_as_markdown(output_path_md)
print(f"Total time: {time.time() - start_time:.2f} sec")

# Prerequisites:
# pip install onnxruntime
# pip install onnxruntime-gpu
from transformers import AutoConfig, AutoProcessor
from transformers.image_utils import load_image
import onnxruntime
import numpy as np
import os
from docling_core.types.doc import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument

os.environ["OMP_NUM_THREADS"] = "1"
# cuda
os.environ["ORT_CUDA_USE_MAX_WORKSPACE"] = "1"

# 1. Load models
## Load config and processor
model_id = "ds4sd/SmolDocling-256M-preview"
config = AutoConfig.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

## Load sessions
# !wget https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/onnx/vision_encoder.onnx
# !wget https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/onnx/embed_tokens.onnx
# !wget https://huggingface.co/ds4sd/SmolDocling-256M-preview/resolve/main/onnx/decoder_model_merged.onnx
# cpu
# vision_session = onnxruntime.InferenceSession("vision_encoder.onnx")
# embed_session = onnxruntime.InferenceSession("embed_tokens.onnx")
# decoder_session = onnxruntime.InferenceSession("decoder_model_merged.onnx"

# cuda
vision_session = onnxruntime.InferenceSession("vision_encoder.onnx", providers=["CUDAExecutionProvider"])
embed_session = onnxruntime.InferenceSession("embed_tokens.onnx", providers=["CUDAExecutionProvider"])
decoder_session = onnxruntime.InferenceSession("decoder_model_merged.onnx", providers=["CUDAExecutionProvider"])

## Set config values
num_key_value_heads = config.text_config.num_key_value_heads
head_dim = config.text_config.head_dim
num_hidden_layers = config.text_config.num_hidden_layers
eos_token_id = config.text_config.eos_token_id
image_token_id = config.image_token_id
end_of_utterance_id = processor.tokenizer.convert_tokens_to_ids("")

# 2. Prepare inputs
## Create input messages
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Convert this page to docling."}
        ]
    },
]

## Load image and apply processor
image = load_image("https://ibm.biz/docling-page-with-table")
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image], return_tensors="np")

## Prepare decoder inputs
batch_size = inputs['input_ids'].shape[0]
past_key_values = {
    f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
    for layer in range(num_hidden_layers)
    for kv in ('key', 'value')
}
image_features = None
input_ids = inputs['input_ids']
attention_mask = inputs['attention_mask']
position_ids = np.cumsum(inputs['attention_mask'], axis=-1)


# 3. Generation loop
max_new_tokens = 8192
generated_tokens = np.array([[]], dtype=np.int64)
for i in range(max_new_tokens):
  inputs_embeds = embed_session.run(None, {'input_ids': input_ids})[0]

  if image_features is None:
    ## Only compute vision features if not already computed
    image_features = vision_session.run(
        ['image_features'],  # List of output names or indices
        {
            'pixel_values': inputs['pixel_values'],
            'pixel_attention_mask': inputs['pixel_attention_mask'].astype(np.bool_)
        }
    )[0]
    
    ## Merge text and vision embeddings
    inputs_embeds[inputs['input_ids'] == image_token_id] = image_features.reshape(-1, image_features.shape[-1])

  logits, *present_key_values = decoder_session.run(None, dict(
      inputs_embeds=inputs_embeds,
      attention_mask=attention_mask,
      position_ids=position_ids,
      **past_key_values,
  ))

  ## Update values for next generation loop
  input_ids = logits[:, -1].argmax(-1, keepdims=True)
  attention_mask = np.ones_like(input_ids)
  position_ids = position_ids[:, -1:] + 1
  for j, key in enumerate(past_key_values):
    past_key_values[key] = present_key_values[j]

  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
  if (input_ids == eos_token_id).all() or (input_ids == end_of_utterance_id).all():
    break  # Stop predicting

doctags = processor.batch_decode(
    generated_tokens,
    skip_special_tokens=False,
)[0].lstrip()

print(doctags)

doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
print(doctags)
# create a docling document
doc = DoclingDocument.load_from_doctags(doctags_doc, document_name="Document")

print(doc.export_to_markdown())