Description #

CLIP (Contrastive Language-Image Pretraining) cross-modal embedding generator, implements image-text joint embedding space mapping based on the CLIP model

Key features #

• Unified multimodal encoding
• Text encoding: Chinese text → 512/768/1024-dimensional semantic vector
• Image encoding: image → 512/768/1024-dimensional visual feature vector
• Cross-modal similarity calculation
• Supports cosine similarity and dot product to calculate the correlation of image-text embedding vectors

Typical application scenarios #

• ✅ E-commerce scenario – product image-text cross-modal search
• ✅ Content moderation – image-text consistency check
• ✅ Recommendation system – multimodal feature fusion

Operator parameters #

Input #

Output #

An array containing floating-point embedding vectors, each element is List[float].

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use daft to run the image-text embedding operator and generate image-text embeddings.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.multimodal.embedding.clip_embedding import ClipEmbedding
from daft.las.functions.udf import las_udf

if __name__ == "__main__":
    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S.%s".format(),
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()
    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    samples = {"text": ["", "", "", None]}
    content_type = "text"
    model_path = os.getenv("MODEL_PATH", "/opt/las/models")
    model_name = "iic/multi-modal_clip-vit-base-patch16_zh"
    model_version = "v1.0.1"
    embedding_col_name = "embedding"
    batch_size = 2
    rank = 0
    num_gpus = 1

    ds = daft.from_pydict(samples)
    ds = ds.with_column(
        "embedding",
        las_udf(
            ClipEmbedding,
            construct_args={
                "content_type": content_type,
                "model_path": model_path,
                "model_name": model_name,
                "model_version": model_version,
                "batch_size": batch_size,
                "rank": rank,
            },
            num_gpus=num_gpus,
            batch_size=1,
            concurrency=1,
        )(col("text")),
    )

    ds.show()

    # ╭────────┬────────────────────────────────╮
    # │ text   ┆ embedding                      │
    # │ ---    ┆ ---                            │
    # │ Utf8   ┆ List[Float32]                  │
    # ╞════════╪════════════════════════════════╡
    # │ 皮卡丘  ┆ [0.12005615, -0.009140015, -0… │
    # ├╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ 小狗    ┆ [0.12963867, 0.00039935112, 0… │
    # ├╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ 小猫    ┆ [0.12670898, 0.015533447, 0.0… │
    # ├╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ None   ┆ None                           │
    # ╰────────┴────────────────────────────────╯

    tos_dir_url = os.getenv("TOS_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    samples = {
        "image_path": [
            f"https://{tos_dir_url}/public/shared_image_dataset/cat_ip_adapter.jpeg"
        ]
    }
    ds = daft.from_pydict(samples)
    ds = ds.with_column(
        "embedding",
        las_udf(
            ClipEmbedding,
            construct_args={
                "content_type": "image_url",
                "model_path": model_path,
                "model_name": model_name,
                "model_version": model_version,
                "batch_size": batch_size,
                "rank": rank,
            },
            num_gpus=num_gpus,
            batch_size=1,
        )(col("image_path")),
    )

    ds.show()

    # ╭────────────────────────────────┬────────────────────────────────╮
    # │ image_path                     ┆ embedding                      │
    # │ ---                            ┆ ---                            │
    # │ Utf8                           ┆ List[Float32]                  │
    # ╞════════════════════════════════╪════════════════════════════════╡
    # │ tos://las-cn-beijing-public-o… ┆ [0.04598999, -0.090148926, -0… │
    # ╰────────────────────────────────┴────────────────────────────────╯