An example using the GemFire Vector Database extension to perform an image search.
An image search webapp that uses VMware GemFire and the VMware GemFire Vector Database extension. Download the extension from the Broadcom Support Portal: GemFire Vector Database extension
Click “Create Index”
Click “Load Embeddings” the application will then
/static/images
backend
Now that the index has been created, images are available, and the embeddings have been loaded into GemFire, you can search for images.
The full image set can also be downloaded here if needed: Image Data Set
If you would like to use your own images data set:
backend/static/images
.jpg
use_precomputed_embeddings
embeddings_processor.py
load_embeddings
When searching images
app.py
/searchImages
top-k:100
embeddings_processor.py -> def create_query_embedding(search_query): Enter your code here ....
--http-service-port
localhost
baseUrl
There are a few python packages you may need to install such as:
Download the VMware GemFire Vector Database extension from the Broadcom Support Portal and put the .gfm file into the GemFire extensions directory.
.gfm
Start a GemFire Shell (gfsh)
In the GemFire Shell, start a GemFire locator
start locator
In the GemFire Shell, start a GemFire server, turning on the rest API and setting the HTTP Port start server --start-rest-api --http-service-port=8081 --name=gemfire-image-search
start server --start-rest-api --http-service-port=8081 --name=gemfire-image-search
frontend
npm install
npm run build
python app.py
To prevent this message from showing again, please enable pop-up blockers for support.broadcom.com or click Continue to proceed.