Clip As Service

Embedding image and sentence into fixed-length vectors via CLIP

CLIP-as-service is a low-latency high-scalability embedding service for images and texts. It can be easily integrated as a microservice into neural search solutions.

⚡ Fast: Serve CLIP models with ONNX runtime and PyTorch JIT with 800QPS^[*]. Non-blocking duplex streaming on requests and responses, designed for large data and long-running tasks.

🫐 Elastic: Horizontally scale up and down multiple CLIP models on single GPU, with automatic load balancing.

🐥 Easy-to-use: No learning curve, minimalist design on client and server. Intuitive and consistent API for image and sentence embedding.

👒 Modern: Async client support. Easily switch between gRPC, HTTP, Websocket protocols with TLS and compressions.

🍱 Integration: Smoothly integrated with neural search ecosystem including Jina and DocArray. Build cross-modal and multi-modal solution in no time.

^{[*] with default config (single replica, PyTorch no JIT) on GeForce RTX 3090.}

Documentation

Install

CLIP-as-service consists of two Python packages clip-server and clip-client that can be installed independently. Both require Python 3.7+.

Install server

pip install clip-server

To run CLIP model via ONNX (default is via PyTorch):

pip install "clip-server[onnx]"

Install client

pip install clip-client

Quick check

You can run a simple connectivity check after install.

C/S	Command	Expect output
Server	python -m clip_server
Client	from clip_client import Client c = Client('grpc://0.0.0.0:23456') c.profile()

You can change 0.0.0.0 to the intranet or public IP address to test the connectivity over private and public network. If you encounter some errors, please find the solution here.

Get Started

Basic usage

1. Start the server: python -m clip_server. Remember its address and port.
2. Create a client:

    from clip_client import Client
   
    c = Client('grpc://87.191.159.105:51000')
   

3. To get sentence embedding:

   r = c.encode(['First do it', 'then do it right', 'then do it better'])
   
   print(r.shape)  # [3, 512] 
   

4. To get image embedding:

   r = c.encode(['apple.png',  # local image 
                 'https://docarray.jina.ai/_static/favicon.png',  # remote image
                 'data:image/gif;base64,R0lGODlhEAAQAMQAAORHHOVSKudfOulrSOp3WOyDZu6QdvCchPGolfO0o/XBs/fNwfjZ0frl3/zy7////wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACH5BAkAABAALAAAAAAQABAAAAVVICSOZGlCQAosJ6mu7fiyZeKqNKToQGDsM8hBADgUXoGAiqhSvp5QAnQKGIgUhwFUYLCVDFCrKUE1lBavAViFIDlTImbKC5Gm2hB0SlBCBMQiB0UjIQA7'])  # in image URI
   
   print(r.shape)  # [3, 512]
   

More comprehensive server & client configs can be found in the docs.

Text-to-image cross-modal search in 10 Lines

Let's build a text-to-image search using CLIP-as-service. Namely, user input a sentence and the program returns the matched images. We will use Totally Looks Like dataset and DocArray package. Note that DocArray is included within clip-client as an upstream dependency, so you don't need to install it separately.

Load images

First we load images. You can simply pull it from Jina Cloud:

from docarray import DocumentArray

da = DocumentArray.pull('ttl-original', show_progress=True, local_cache=True)

from docarray import DocumentArray

da = DocumentArray.from_files(['left/*.jpg', 'right/*.jpg'])

The dataset contains 12,032 images, hence it may take half minute to pull. Once done, you can visualize it and get the first taste of those images.

da.plot_image_sprites()

Encode images

Start the server with python -m clip_server. Say it is at 87.191.159.105:51000 with GRPC protocol (you will get this information after running the server).

Create a Python client script:

from clip_client import Client

c = Client(server='grpc://87.191.159.105:51000')

da = c.encode(da, show_progress=True)

Depending on your GPU and client-server network, it could take a while to embed 12K images. In my case, it takes ~2 minute.

from docarray import DocumentArray

da = DocumentArray.pull('ttl-embedding', show_progress=True, local_cache=True)

Search via sentence

Let's build a simple prompt to allow user to type sentence:

while True:
    vec = c.encode([input('sentence> ')])
    r = da.find(query=vec, limit=9)
    r.plot_image_sprites()

Showcase

Now you can input arbitrary English sentences and view the top-9 matched images. Search is fast and instinct. Let's have some fun:

Let's save the embedding result for our next example:

da.save_binary('ttl-image')

Image-to-text cross-modal search in 10 Lines

We can also switch the input and output of the last program to achieve image-to-text search. Precisely, given a query image find the sentence that best describes the image.

Let's use all sentences from the book "Pride and Prejudice".

from docarray import Document, DocumentArray

d = Document(uri='https://www.gutenberg.org/files/1342/1342-0.txt').load_uri_to_text()
da = DocumentArray(
    Document(text=s.strip()) for s in d.text.replace('\r\n', '').split('.') if s.strip()
)

Let's look at what we got:

da.summary()

            Documents Summary            
                                         
  Length                 6403            
  Homogenous Documents   True            
  Common Attributes      ('id', 'text')  
                                         
                     Attributes Summary                     
                                                            
  Attribute   Data type   #Unique values   Has empty value  
 ────────────────────────────────────────────────────────── 
  id          ('str',)    6403             False            
  text        ('str',)    6030             False            

Encode sentences

Now encode these 6403 sentences, it may take 10s or less depending on your GPU and network:

from clip_client import Client

c = Client('grpc://87.191.159.105:51000')

r = c.encode(da, show_progress=True)

from docarray import DocumentArray

da = DocumentArray.pull('ttl-textual', show_progress=True, local_cache=True)

Search via image

Let's load our previously stored image embedding; randomly sample image Document from it, then find top-1 nearest neighbour of each.

from docarray import DocumentArray

img_da = DocumentArray.load_binary('ttl-image')

for d in img_da.sample(10):
    print(da.find(d.embedding, limit=1)[0].text)

Showcase

Fun time! Note, unlike the previous example, here the input is an image, the sentence is the output. All sentences come from the book "Pride and Prejudice".

Intrigued? That's only scratching the surface of what CLIP-as-service is capable of. Read our docs to learn more.

Support

• Use Discussions to talk about your use cases, questions, and support queries.
• Join our Slack community and chat with other community members about ideas.
• Join our Engineering All Hands meet-up to discuss your use case and learn Jina's new features.
  • When? The second Tuesday of every month
  • Where? Zoom (see our public events calendar/.ical) and live stream on YouTube
• Subscribe to the latest video tutorials on our YouTube channel

Join Us

CLIP-as-service is backed by Jina AI and licensed under Apache-2.0. We are actively hiring AI engineers, solution engineers to build the next neural search ecosystem in open-source.