demo.py

from ops_mm_embedding_v1 import OpsMMEmbeddingV1, fetch_image


model = OpsMMEmbeddingV1(
    "OpenSearch-AI/Ops-MM-embedding-v1-2B",
    device="cuda",
    attn_implementation="flash_attention_2"
)

t2i_prompt = "Find an image that matches the given text."
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
    "Alibaba office.",
]
images = [
    "https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/thumb/b/b0/Alibaba_Binjiang_Park.jpg/1024px-Alibaba_Binjiang_Park.jpg"
]

images = [fetch_image(image) for image in images]

# Text and image embedding
text_embeddings = model.get_text_embeddings(texts)
image_embeddings = model.get_image_embeddings(images)
print('Text and image embeddings', (text_embeddings @ image_embeddings.T).tolist())

# Fused Embedding
text_with_image_embeddings = model.get_fused_embeddings(texts=texts, images=images, instruction=t2i_prompt)
print('Text and image embeddings', (text_embeddings @ image_embeddings.T).tolist())

# Multi-image embeddings
multi_images = [
    [images[0]],
    [images[1], images[2]],
]
multi_image_embeddings = model.get_image_embeddings(multi_images)
print('Multi-image embeddings', (multi_image_embeddings @ multi_image_embeddings.T).tolist())