Embed images and sentences into fixed-length vectors with CLIP

CLIP-as-service is a low-latency high-scalability service for embedding images and text. 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 compression.

🍱 Integration: Smooth integration with neural search ecosystem including Jina and DocArray. Build cross-modal and multi-modal solutions in no time.

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

Try it!

curl -X POST http://demo-cas.jina.ai:51001/post -H 'Content-Type: application/json' \
     -d '{"data":[{"text": "hello, world!"}, {"uri": "https://clip-as-service.jina.ai/_static/favicon.png" }], "execEndpoint":"/"}'

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.

Demo server

We provide a demo server for you to play with:

from clip_client import Client

c = Client('grpc://demo-cas.jina.ai:51000')

print(c.encode(['First do it', 'then do it right', 'then do it better']))

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://87.105.159.191:51000')

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://clip-as-service.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 and client user guides 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, a user can input a sentence and the program returns matching images. We'll use the 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 them from Jina Cloud:

from docarray import DocumentArray

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

or download TTL dataset, unzip, load manually

Alternatively, you can go to Totally Looks Like official website, unzip and load images:

from docarray import DocumentArray

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

The dataset contains 12,032 images, so it may take a while 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. Let's say it's at 87.105.159.191:51000 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://87.105.159.191:51000')

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

Depending on your GPU and client-server network, it may take a while to embed 12K images. In my case, it took about two minutes.

Download the pre-encoded dataset

If you're impatient or don't have a GPU, waiting can be Hell. In this case, you can simply pull our pre-encoded image dataset:

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 a user to type sentence:

while True:
    vec = c.encode([input('sentence> ')])
    r = da.find(query=vec, limit=9)
    r[0].plot_image_sprites()

Showcase

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

"a happy potato"	"a super evil AI"	"a guy enjoying his burger"

"professor cat is very serious"	"an ego engineer lives with parent"	"there will be no tomorrow so lets eat unhealthy"

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 6,403 sentences, it may take 10 seconds or less depending on your GPU and network:

from clip_client import Client

c = Client('grpc://87.105.159.191:51000')

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

Download the pre-encoded dataset

Again, for people who are impatient or don't have a GPU, we have prepared a pre-encoded text dataset:

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 10 image Documents, 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 and the sentence is the output. All sentences come from the book "Pride and Prejudice".

Besides, there was truth in his looks	Gardiner smiled	what’s his name	By tea time, however, the dose had been enough, and Mr	You do not look well

“A gamester!” she cried	If you mention my name at the Bell, you will be attended to	Never mind Miss Lizzy’s hair	Elizabeth will soon be the wife of Mr	I saw them the night before last

Rank image-text matches via CLIP model

From 0.3.0 CLIP-as-service adds a new /rank endpoint that re-ranks cross-modal matches according to their joint likelihood in CLIP model. For example, given an image Document with some predefined sentence matches as below:

from clip_client import Client
from docarray import Document

c = Client(server='grpc://demo-cas.jina.ai:51000')
r = c.rank(
    [
        Document(
            uri='.github/README-img/rerank.png',
            matches=[
                Document(text=f'a photo of a {p}')
                for p in (
                    'control room',
                    'lecture room',
                    'conference room',
                    'podium indoor',
                    'television studio',
                )
            ],
        )
    ]
)

print(r['@m', ['text', 'scores__clip_score__value']])

[['a photo of a television studio', 'a photo of a conference room', 'a photo of a lecture room', 'a photo of a control room', 'a photo of a podium indoor'], 
[0.9920725226402283, 0.006038925610482693, 0.0009973491542041302, 0.00078492151806131, 0.00010626466246321797]]

One can see now a photo of a television studio is ranked to the top with clip_score score at 0.992. In practice, one can use this endpoint to re-rank the matching result from another search system, for improving the cross-modal search quality.

Rank text-image matches via CLIP model

In the DALL·E Flow project, CLIP is called for ranking the generated results from DALL·E. It has an Executor wrapped on top of clip-client, which calls .arank() - the async version of .rank():

from clip_client import Client
from jina import Executor, requests, DocumentArray


class ReRank(Executor):
    def __init__(self, clip_server: str, **kwargs):
        super().__init__(**kwargs)
        self._client = Client(server=clip_server)

    @requests(on='/')
    async def rerank(self, docs: DocumentArray, **kwargs):
        return await self._client.arank(docs)

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.