llamaindex/vdr-2b-multi-v1

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|>"

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)

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")