clip_embedding/README.md

CLIP Embedding Service

CLIP-ViT-H/14 多模态 Embedding 服务，支持文本和图片向量化。

Overview

• Model: laion/CLIP-ViT-H-14-laion2B-s32B-b79K
• Dimension: 1024
• Precision: float16
• Port: 9086
• GPU: 2 (default)

API

GET /api/status

Service health and GPU info.

POST /api/text

Text embedding.

{"texts": ["hello world", "a cat"]}

POST /api/image

Image embedding (file path, URL, or base64 data URI).

{"images": ["/path/to/img.jpg", "https://example.com/img.png"]}

POST /api/embed

Combined text + image embedding.

{"texts": ["a cat"], "images": ["/path/to/cat.jpg"]}

Model Download (Offline Deploy)

pip install huggingface_hub
huggingface-cli download laion/CLIP-ViT-H-14-laion2B-s32B-b79K \
  --local-dir /data/ymq/models/laion/CLIP-ViT-H-14-laion2B-s32B-b79K \
  --local-dir-use-symlinks False

Size: ~15GB

Deploy

bash build.sh deploy    # start
bash build.sh stop      # stop
bash build.sh status    # check