Spaces:
Running
on
Zero
Running
on
Zero
File size: 2,908 Bytes
f3d315e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
from colpali_engine.models import ColPali
from colpali_engine.models.paligemma.colpali.processing_colpali import ColPaliProcessor
from colpali_engine.utils.processing_utils import BaseVisualRetrieverProcessor
from colpali_engine.utils.torch_utils import ListDataset, get_torch_device
from torch.utils.data import DataLoader
import torch
from typing import List, cast
from tqdm import tqdm
from PIL import Image
import os
import spaces
model_name = "vidore/colpali-v1.2"
device = get_torch_device("cuda")
model = ColPali.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map=device,
).eval()
processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name))
class ColpaliManager:
def __init__(self, device = "cuda", model_name = "vidore/colpali-v1.2"):
print(f"Initializing ColpaliManager with device {device} and model {model_name}")
# self.device = get_torch_device(device)
# self.model = ColPali.from_pretrained(
# model_name,
# torch_dtype=torch.bfloat16,
# device_map=self.device,
# ).eval()
# self.processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name))
@spaces.GPU
def get_images(self, paths: list[str]) -> List[Image.Image]:
return [Image.open(path) for path in paths]
@spaces.GPU
def process_images(self, image_paths:list[str], batch_size=5):
print(f"Processing {len(image_paths)} image_paths")
images = self.get_images(image_paths)
dataloader = DataLoader(
dataset=ListDataset[str](images),
batch_size=batch_size,
shuffle=False,
collate_fn=lambda x: processor.process_images(x),
)
ds: List[torch.Tensor] = []
for batch_doc in tqdm(dataloader):
with torch.no_grad():
batch_doc = {k: v.to(model.device) for k, v in batch_doc.items()}
embeddings_doc = model(**batch_doc)
ds.extend(list(torch.unbind(embeddings_doc.to(device))))
ds_np = [d.float().cpu().numpy() for d in ds]
return ds_np
@spaces.GPU
def process_text(self, texts: list[str]):
print(f"Processing {len(texts)} texts")
dataloader = DataLoader(
dataset=ListDataset[str](texts),
batch_size=1,
shuffle=False,
collate_fn=lambda x: processor.process_queries(x),
)
qs: List[torch.Tensor] = []
for batch_query in dataloader:
with torch.no_grad():
batch_query = {k: v.to(model.device) for k, v in batch_query.items()}
embeddings_query = model(**batch_query)
qs.extend(list(torch.unbind(embeddings_query.to(device))))
qs_np = [q.float().cpu().numpy() for q in qs]
return qs_np
|