pip install -q datasets transformers

from datasets import load_dataset

dataset = load_dataset("davanstrien/ufo-ColPali")
dataset = dataset["train"]
dataset = dataset.filter(lambda example: example["specific_detail_query"] is not None)
print(dataset)

Dataset({
    features: ['image', 'raw_queries', 'broad_topical_query', 'broad_topical_explanation', 'specific_detail_query', 'specific_detail_explanation', 'visual_element_query', 'visual_element_explanation', 'parsed_into_json'],
    num_rows: 2172
})

import torch
from transformers import ColPaliForRetrieval, ColPaliProcessor
from accelerate import Accelerator

device = Accelerator().device

model_name = "vidore/colpali-v1.2-hf"

processor = ColPaliProcessor.from_pretrained(model_name)

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    dtype=torch.bfloat16,
    device_map="auto",
).eval()

inputs = processor(text="a document about Mars expedition").to(model.device)
with torch.no_grad():
  text_embeds = model(**inputs, return_tensors="pt").embeddings

ds_with_embeddings = dataset.map(lambda example: {'embeddings': model(**processor(images=example["image"]).to(device), return_tensors="pt").embeddings.to(torch.float32).detach().cpu().numpy()})

def find_top_k_indices_batched(dataset, text_embedding, processor, k=10, batch_size=4):
    scores_and_indices = []

    for start_idx in range(0, len(dataset), batch_size):

        end_idx = min(start_idx + batch_size, len(dataset))
        batch = dataset[start_idx:end_idx]        
        batch_embeddings = [torch.tensor(emb[0], dtype=torch.float32) for emb in batch["embeddings"]]
        scores = processor.score_retrieval(text_embedding.to("cpu").to(torch.float32), batch_embeddings)

        if hasattr(scores, "tolist"):
            scores = scores.tolist()[0]

        for i, score in enumerate(scores):
            scores_and_indices.append((score, start_idx + i))

    sorted_results = sorted(scores_and_indices, key=lambda x: -x[0])

    topk = sorted_results[:k]
    indices = [idx for _, idx in topk]
    scores = [score for score, _ in topk]

    return indices, scores

with torch.no_grad():
  text_embeds = model(**processor(text="a document about Mars expedition").to(model.device), return_tensors="pt").embeddings
indices, scores = find_top_k_indices_batched(ds_with_embeddings, text_embeds, processor, k=3, batch_size=4)
print(indices, scores)

([440, 442, 443],
 [14.370786666870117,
  13.675487518310547,
  12.9899320602417])

for i in indices:
  display(dataset[i]["image"])