Image Search Demo

Getting Started

1. Clone the examples repository.

2. Run Marqo:

   docker rm -f marqo
   docker pull marqoai/marqo:latest
   docker run --name marqo -it --privileged -p 8882:8882 --add-host host.docker.internal:host-gateway marqoai/marqo:latest
   

   For mode detailed instructions, check the getting started guide.

3. Follow the instructions below or see the original code and article here.

Code

Example

import marqo
mq = marqo.Client("http://localhost:8882")

mq.get_marqo()

# {'message': 'Welcome to Marqo', 'version': 'X.X.X'}

####################################################
### STEP 1: Download Data
####################################################

# Download the data from [here](https://github.com/marqo-ai/marqo/tree/mainline/examples/ImageSearchGuide/data)
# store it in a data/ directory

#####################################################
### STEP 2. Start Marqo
#####################################################

# Follow the instructions here https://github.com/marqo-ai/marqo or see below
"""
docker rm -f marqo
docker pull marqoai/marqo:latest
docker run --name marqo -it --privileged -p 8882:8882 --add-host host.docker.internal:host-gateway marqoai/marqo:latest
"""

####################################################
### STEP 3: Index Data
####################################################

index_name = 'image-search-guide'

settings = {
        "model": "ViT-L/14",
        "treat_urls_and_pointers_as_images": True,
        }

mq.create_index(index_name, **settings)

####################################################
### STEP 4: Access Local Images
####################################################

import subprocess
local_dir = "./data"
pid = subprocess.Popen(['python3', '-m', 'http.server', '8222', '--directory', local_dir], stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)

import glob
import os

# Find all the local images
locators = glob.glob(local_dir + '*.jpg')

# Generate docker path for local images
docker_path = "http://host.docker.internal:8222/"
image_docker = [docker_path + os.path.basename(f) for f in locators]

print(image_docker)

"""
output:
['http://host.docker.internal:8222/image4.jpg',
'http://host.docker.internal:8222/image1.jpg',
'http://host.docker.internal:8222/image3.jpg',
'http://host.docker.internal:8222/image0.jpg',
'http://host.docker.internal:8222/image2.jpg']
"""

####################################################
### STEP 5: Add Images to the Index
####################################################

documents = [{"image_docker" : image, "_id" : idx} for idx, image in enumerate(image_docker)]

print(documents)

mq.index(index_name).add_documents(
    documents, device="cpu", client_batch_size= 1,
    tensor_fields=["image_docker"]
) 

####################################################
### STEP 6: Search using Marqo
####################################################

search_results =  mq.index(index_name).search("A rider on a horse jumping over the barrier", 
                    searchable_attributes=['image_docker'], limit = 1,
                    device='cpu')
print(search_results)


####################################################
### STEP 7: Visualize the Output
####################################################

import requests
from PIL import Image

fig_path = search_results["hits"][0]["image_docker"].replace(docker_path, local_dir)
display(Image.open(fig_path))