Skip to content

πŸ„ Scalable embedding, reasoning, ranking for images and sentences with CLIP

License

Notifications You must be signed in to change notification settings

santlchogva/clip-as-service

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

CLIP-as-service logo: The data structure for unstructured data


PyPI Codecov branch Host on Google Colab with GPU/TPU support

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 TensorRT, ONNX runtime and PyTorch w/o 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.

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

πŸ‘’ 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.

Text & image embedding

via HTTPS πŸ” via gRPC πŸ”βš‘βš‘
curl \
-X POST https://<your-inference-address>-http.wolf.jina.ai/post \
-H 'Content-Type: application/json' \
-H 'Authorization: <your access token>' \
-d '{"data":[{"text": "First do it"}, 
    {"text": "then do it right"}, 
    {"text": "then do it better"}, 
    {"uri": "https://picsum.photos/200"}], 
    "execEndpoint":"/"}'
# pip install clip-client
from clip_client import Client

c = Client(
    'grpcs://<your-inference-address>-grpc.wolf.jina.ai',
    credential={'Authorization': '<your access token>'},
)

r = c.encode(
    [
        'First do it',
        'then do it right',
        'then do it better',
        'https://picsum.photos/200',
    ]
)
print(r)

Visual reasoning

There are four basic visual reasoning skills: object recognition, object counting, color recognition, and spatial relation understanding. Let's try some:

You need to install jq (a JSON processor) to prettify the results.

Image via HTTPS πŸ”
curl \
-X POST https://<your-inference-address>-http.wolf.jina.ai/post \
-H 'Content-Type: application/json' \
-H 'Authorization: <your access token>' \
-d '{"data":[{"uri": "https://picsum.photos/id/1/300/300",
"matches": [{"text": "there is a woman in the photo"},
            {"text": "there is a man in the photo"}]}],
            "execEndpoint":"/rank"}' \
| jq ".data[].matches[] | (.text, .scores.clip_score.value)"

gives:

"there is a woman in the photo"
0.626907229423523
"there is a man in the photo"
0.37309277057647705
curl \
-X POST https://<your-inference-address>-http.wolf.jina.ai/post \
-H 'Content-Type: application/json' \
-H 'Authorization: <your access token>' \
-d '{"data":[{"uri": "https://picsum.photos/id/133/300/300",
"matches": [
{"text": "the blue car is on the left, the red car is on the right"},
{"text": "the blue car is on the right, the red car is on the left"},
{"text": "the blue car is on top of the red car"},
{"text": "the blue car is below the red car"}]}],
"execEndpoint":"/rank"}' \
| jq ".data[].matches[] | (.text, .scores.clip_score.value)"

gives:

"the blue car is on the left, the red car is on the right"
0.5232442617416382
"the blue car is on the right, the red car is on the left"
0.32878655195236206
"the blue car is below the red car"
0.11064132302999496
"the blue car is on top of the red car"
0.03732786327600479
curl \
-X POST https://<your-inference-address>-http.wolf.jina.ai/post \
-H 'Content-Type: application/json' \
-H 'Authorization: <your access token>' \
-d '{"data":[{"uri": "https://picsum.photos/id/102/300/300",
"matches": [{"text": "this is a photo of one berry"},
            {"text": "this is a photo of two berries"},
            {"text": "this is a photo of three berries"},
            {"text": "this is a photo of four berries"},
            {"text": "this is a photo of five berries"},
            {"text": "this is a photo of six berries"}]}],
            "execEndpoint":"/rank"}' \
| jq ".data[].matches[] | (.text, .scores.clip_score.value)"

gives:

"this is a photo of three berries"
0.48507222533226013
"this is a photo of four berries"
0.2377079576253891
"this is a photo of one berry"
0.11304923892021179
"this is a photo of five berries"
0.0731358453631401
"this is a photo of two berries"
0.05045759305357933
"this is a photo of six berries"
0.04057715833187103

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

Pytorch Runtime ⚑ ONNX Runtime ⚑⚑ TensorRT Runtime ⚑⚑⚑
pip install clip-server
pip install "clip-server[onnx]"
pip install nvidia-pyindex 
pip install "clip-server[tensorrt]"

You can also host the server on Google Colab, leveraging its free GPU/TPU.

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
Expected server output
Client
from clip_client import Client

c = Client('grpc://0.0.0.0:23456')
c.profile()
Expected clip-client output

You can change 0.0.0.0 to the intranet or public IP address to test the connectivity over private and public network.

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://0.0.0.0:51000')
  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()

Visualization of the image sprite of Totally looks like dataset

Encode images

Start the server with python -m clip_server. Let's say it's at 0.0.0.0:51000 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://0.0.0.0:51000')

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"

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

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

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

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://0.0.0.0:51000')

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".

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

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

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

Visualization of the image sprite of Totally looks like dataset

β€œA 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://0.0.0.0:51000')
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.

Rerank endpoint image input Rerank endpoint output

Rank text-image matches via CLIP model

In the DALLΒ·E Flow project, CLIP is called for ranking the generated results from DALLΒ·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)

CLIP-as-service used in DALLE Flow

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

Support

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.

About

πŸ„ Scalable embedding, reasoning, ranking for images and sentences with CLIP

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 94.2%
  • Shell 3.1%
  • Dockerfile 2.7%