vdr-2b-multi-v1

vdr-2b-multi-v1 is a multilingual embedding model designed for visual document retrieval across multiple languages and domains. It encodes document page screenshots into dense single-vector representations, this will effectively allow to search and query visually rich multilingual documents without the need for any OCR, data extraction pipelines, chunking...

• Trained on 🇮🇹 Italian, 🇪🇸 Spanish, 🇬🇧 English, 🇫🇷 French and 🇩🇪 German: together they form a new large, open-source, multilingual training dataset of 500k high-quality samples.

• Cross-lingual Retrieval: substantially better on real-world scenarios. For example, this allows for searching german documents with italian queries.

• Matryoshka Representation Learning: You can reduce the vectors size 3x and still keep 98% of the embeddings quality.

Usage

The model uses bf16 tensors and allocates ~4.4GB of VRAM when loaded. You can easily run inference and generate embeddings using 768 image patches and a batch size of 16 even on a cheap NVIDIA T4 GPU. This table reports the memory footprint (GB) under conditions of different batch sizes with HuggingFace Transformers and maximum 768 image patches.

You can generate embeddings with this model in many different ways:

pip install -U llama-index-embeddings-huggingface

from llama_index.embeddings.huggingface import HuggingFaceEmbedding

model = HuggingFaceEmbedding(
    model_name="llamaindex/vdr-2b-multi-v1",
    device="cpu",  # "mps" for mac, "cuda" for nvidia GPUs
    trust_remote_code=True,
)

image_embedding = model.get_image_embedding("image.png")
query_embedding = model.get_query_embedding("some query")

from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
from PIL import Image
import torch
import math

# more pixels -> better embeddings -> more VRAM -> slower inference
# From my experience, 768 image patches is the right spot for compute efficient embeddings.
max_pixels = 768 * 28 * 28
min_pixels = 1 * 28 * 28

# Load the embedding model and processor
model = Qwen2VLForConditionalGeneration.from_pretrained(
    'llamaindex/vdr-2b-multi-v1',
    # These are the recommended kwargs for the model, but change them as needed
    attn_implementation="flash_attention_2",
    torch_dtype=torch.bfloat16,
    device_map="cuda:0"
).eval()

processor = AutoProcessor.from_pretrained(
    'llamaindex/vdr-2b-multi-v1',
    min_pixels=min_pixels,
    max_pixels=max_pixels
)

model.padding_side = "left"
processor.tokenizer.padding_side = "left"

document_prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>What is shown in this image?<|im_end|>\n<|endoftext|>"

query_prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Query: %s<|im_end|>\n<|endoftext|>"

Encode queries

def encode_queries(queries: list[str], dimension: int) -> torch.Tensor:
    """
    Encode a list of queries into a tensor of embeddings.

    Args:
        queries: A list of strings, each representing a query.
        dimension: The desired dimension of the output embeddings.

    Returns:
        A tensor of shape (num_queries, dimension) containing the encoded queries.
    """

    dummy_image = Image.new('RGB', (56, 56))
    inputs = processor(
        text=[query_prompt % x for x in queries],
        images=[dummy_image for _ in queries],
        videos=None,
        padding='longest',
        return_tensors='pt'
    ).to('cuda:0')

    cache_position = torch.arange(0, len(queries))
    inputs = model.prepare_inputs_for_generation(
        **inputs, cache_position=cache_position, use_cache=False)

    with torch.no_grad():
        output = self.model(
            **inputs,
            return_dict=True,
            output_hidden_states=True
        )

    embeddings = output.hidden_states[-1][:, -1]
    return torch.nn.functional.normalize(embeddings[:, :dimension], p=2, dim=-1)

Encode documents

def round_by_factor(number: float, factor: int) -> int:
    return round(number / factor) * factor

def ceil_by_factor(number: float, factor: int) -> int:
    return math.ceil(number / factor) * factor

def floor_by_factor(number: float, factor: int) -> int:
    return math.floor(number / factor) * factor

def smart_resize(height: int, width: int) -> tuple[int, int]:
    h_bar = max(28, round_by_factor(height, 28))
    w_bar = max(28, round_by_factor(width, 28))
    if h_bar * w_bar > max_pixels:
        beta = math.sqrt((height * width) / max_pixels)
        h_bar = floor_by_factor(height / beta, 28)
        w_bar = floor_by_factor(width / beta, 28)
    elif h_bar * w_bar < min_pixels:
        beta = math.sqrt(min_pixels / (height * width))
        h_bar = ceil_by_factor(height * beta, 28)
        w_bar = ceil_by_factor(width * beta, 28)
    return w_bar, h_bar

def resize(image: Image.Image):
    new_size = smart_resize(image.height, image.width)
    return image.resize(new_size)

def encode_documents(documents: list[Image.Image], dimension: int):
    """
    Encode a list of images into a tensor of embeddings.

    Args:
        documents: A list of PIL Image objects.
        dimension: The desired dimension of the output embeddings.

    Returns:
        A tensor of shape (num_documents, dimension) containing the encoded images.
    """
    
    inputs = processor(
        text=[document_prompt] * len(documents),
        images=[resize(x) for x in documents],
        videos=None,
        padding='longest',
        return_tensors='pt'
    ).to('cuda:0')

    cache_position = torch.arange(0, len(queries))
    inputs = model.prepare_inputs_for_generation(
        **inputs, cache_position=cache_position, use_cache=False)

    with torch.no_grad():
        output = self.model(
            **inputs,
            return_dict=True,
            output_hidden_states=True
        )
    
    embeddings = output.hidden_states[-1][:, -1]
    return torch.nn.functional.normalize(embeddings[:, :dimension], p=2, dim=-1)

from sentence_transformers import SentenceTransformer

model = SentenceTransformer(
    model_name_or_path="llamaindex/vdr-2b-multi-v1",
    device="cuda",
    trust_remote_code=True,
    # These are the recommended kwargs for the model, but change them as needed if you don't have CUDA
    model_kwargs={
        "torch_dtype": torch.bfloat16, 
        "device_map": "cuda:0", 
        "attn_implementation": "flash_attention_2"
    },
)

embeddings = model.encode("image.png")

Training

The model is based on MrLight/dse-qwen2-2b-mrl-v1 and it was trained on the new vdr-multilingual-train dataset that consinsists of 500k high quality, multilingual query image pairs. It was trained for 1 epoch using the DSE approach, with a batch size of 128 and hard-mined negatives.

Results

The model has been evaluated on the Vidore benchmark and on custom-built evaluation sets that allow testing its multilingual capabilities on text-only, visual-only and mixed page screenshots. The evaluation dataset is publicly available here on HuggingFace.

All evaluations are performed by calculating NDCG@5 scores using 1536 dimensions vectors and an image resolution that can be represented with maximum 768 tokens.