from colpali_engine.models.gemma3.colgemma3 import ColGemma3, ColGemmaProcessor3
from PIL import Image
import torch

# Load model and processor
model = ColGemma3.from_pretrained("Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear-v1", torch_dtype=torch.bfloat16, device_map="auto")
processor = ColGemmaProcessor3.from_pretrained("Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear-v1")

# Process images
images = [Image.open("document.png")]
batch_images = processor.process_images(images).to(model.device)

# Process queries
queries = ["What is this document about?"]
batch_queries = processor.process_queries(queries).to(model.device)

# Generate embeddings
with torch.no_grad():
    img_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Compute similarity scores
scores = processor.score([query_embeddings[0]], [img_embeddings[0]])

Citation

Base: Gemma3 vision-language model
Vision Encoder: Processes images into patch embeddings
Custom Projection: Projects embeddings to 128 dimensions
Retrieval: Uses MaxSim scoring for multi-vector retrieval

If you use this model, please cite the original ColGemma3 work and the source models.

This model was automatically merged using Modal infrastructure.