Image search

Image search uses an image as a search input to perform vector similarity search.

Additional information

Configure image search

To use images as search inputs, configure an image vectorizer integration for your collection. See the model provider integrations page for a list of available integrations.

By local image path

Use the Near Image operator to execute image search.
If your query image is stored in a file, you can use the client library to search by its filename.

Python

from pathlib import Path

dogs = client.collections.use("Dog")
response = dogs.query.near_image(
    near_image=Path("./images/search-image.jpg"),  # Provide a `Path` object
    return_properties=["breed"],
    limit=1,
    # targetVector: "vector_name" # required when using multiple named vectors
)

print(response.objects[0])

client.close()

  API docs

JS/TS

  const myCollection = client.collections.use('Dog');

  // Query based on the image content
  const result = await myCollection.query.nearImage('./images/search-image.jpg', {
    returnProperties: ['breed'],
    limit: 1,
    // targetVector: 'vector_name' // required when using multiple named vectors
  })

  console.log(JSON.stringify(result.objects, null, 2));

  API docs

Go

response, err := client.GraphQL().Get().
  WithClassName("Dog").
  WithFields(graphql.Field{Name: "breed"}).
  WithNearImage((&graphql.NearImageArgumentBuilder{}).WithImage("image.jpg")).
  WithLimit(1).
  Do(ctx)

  API docs

Java

NearImageArgument nearImage = NearImageArgument.builder()
  .imageFile(new File("./images/search-image.jpg"))
  .build();

Fields fields = Fields.builder()
  .fields(new Field[]{
    Field.builder().name("Breed").build()
  })
  .build();

String query = GetBuilder.builder()
  .className(className)
  .fields(fields)
  .withNearImageFilter(nearImage)
  .limit(1)
  .build()
  .buildQuery();

Result<GraphQLResponse> result = client.graphQL().raw().withQuery(query).run();

  API docs

Example response

By the base64 representation

You can search by a base64 representation of an image:

Python

base64_string="SOME_BASE_64_REPRESENTATION"

# Get the collection containing images
dogs = client.collections.use("Dog")

# Perform query
response = dogs.query.near_image(
    near_image=base64_string,
    return_properties=["breed"],
    limit=1,
    # targetVector: "vector_name" # required when using multiple named vectors
)

print(response.objects[0])

client.close()

  API docs

JS/TS

  import { toBase64FromMedia } from 'weaviate-client';

  const myCollection = client.collections.use('Dog');
  const filePath = './images/search-image.jpg'
  const base64String = await toBase64FromMedia(file.path)

  // Perform query
  const result = await myCollection.query.nearImage(base64String, {
    returnProperties: ['breed'],
    limit: 1,
    // targetVector: 'vector_name' // required when using multiple named vectors
  })

  console.log(JSON.stringify(result.objects, null, 2));

  API docs

Go

response, err := client.GraphQL().Get().
  WithClassName("Dog").
  WithFields(graphql.Field{Name: "breed"}).
  WithNearImage((&graphql.NearImageArgumentBuilder{}).WithImage(base64String)).
  WithLimit(1).
  Do(ctx)

  API docs

Java

String base64_string = "SOME_BASE_64_REPRESENTATION";

NearImageArgument nearImage = NearImageArgument.builder()
  .image(base64_string)
  .build();

Fields fields = Fields.builder()
  .fields(new Field[]{
    Field.builder().name("Breed").build()
  })
  .build();

String query = GetBuilder.builder()
  .className(className)
  .fields(fields)
  .withNearImageFilter(nearImage)
  .limit(1)
  .build()
  .buildQuery();

Result<GraphQLResponse> result = client.graphQL().raw().withQuery(query).run();

  API docs

Example response

{
  "data": {
    "Get": {
      "Dog": [
        {
          "breed": "Corgi"
        }
      ]
    }
  }
}

client.close()

Create a base64 representation of an online image.

You can create a base64 representation of an online image, and use it as input for similarity search as shown above.

Python

import base64, requests

def url_to_base64(url):
    image_response = requests.get(url)
    content = image_response.content
    return base64.b64encode(content).decode("utf-8")

base64_img = url_to_base64("https://upload.wikimedia.org/wikipedia/commons/thumb/1/14/Deutsches_Museum_Portrait_4.jpg/500px-Deutsches_Museum_Portrait_4.jpg")

client.close()

  API docs

JS/TS

const imageURL = 'https://upload.wikimedia.org/wikipedia/commons/thumb/1/14/Deutsches_Museum_Portrait_4.jpg/500px-Deutsches_Museum_Portrait_4.jpg'

async function urlToBase64(imageUrl: string) {
  const response = await fetch(imageUrl);
  const content = await response.buffer();
  return content.toString('base64');
}

const base64 = await urlToBase64(imageURL)
console.log(base64)

  API docs

Go

resp, err := http.Get(url)
if err != nil {
  return "", err
}
defer resp.Body.Close()

content, err := ioutil.ReadAll(resp.Body)
if err != nil {
  return "", err
}

base64string := base64.StdEncoding.EncodeToString(content)

  API docs

Java

try {
  // Open the input stream for the image URL
  URL url = new URL("https://upload.wikimedia.org/wikipedia/commons/thumb/1/14/Deutsches_Museum_Portrait_4.jpg/500px-Deutsches_Museum_Portrait_4.jpg");
  InputStream inputStream = url.openStream();
  // Read the image bytes into a ByteArrayOutputStream
  ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
  byte[] buffer = new byte[8192];
  int bytesRead;
  while ((bytesRead = inputStream.read(buffer)) != -1) {
    outputStream.write(buffer, 0, bytesRead);
  }
  // Convert the bytes to a base64 encoded string
  byte[] imageBytes = outputStream.toByteArray();
  String base64String = Base64.getEncoder().encodeToString(imageBytes);
  System.out.println(base64String);

  inputStream.close();
  outputStream.close();
} catch (IOException e) {
  System.err.println("Error occurred while converting image to base64: " + e.getMessage());
  e.printStackTrace();
}

  API docs

Combination with other operators

A Near Image search can be combined with any other operators (like filter, limit, etc.), just as other similarity search operators.

See the similarity search page for more details.

Related pages

• Connect to Weaviate

Questions and feedback

If you have any questions or feedback, let us know in the user forum.

Technical questions

If you have questions feel free to post on our Community forum.

Documentation feedback

Leave feedback by opening a GitHub issue.