Get Started Guide#

  • Time to Complete: 10 mins

  • Programming Language: Python

Get Started#

Prerequisites#

Step 1: Get the docker images#

Option 1: build from source#

Clone the source code repository if you don’t have it

git clone https://github.com/open-edge-platform/edge-ai-libraries.git
cd edge-ai-libraries/microservices

Run the command to build images:

docker build -t retriever-milvus:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg no_proxy=$no_proxy -f vector-retriever/milvus/src/Dockerfile .

# build the dependency image
cd multimodal-embedding-serving
docker build -t multimodal-embedding-serving:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg no_proxy=$no_proxy -f docker/Dockerfile .

Option 2: use remote prebuilt images#

Set a remote registry by exporting environment variables:

export REGISTRY="intel/"  
export TAG="latest"

Step 2: Deploy#

Deploy the application together with the Milvus Server#

  1. Go to the deployment files

    cd deployment/docker-compose/

  2. Set up environment variables, note that you need to set an embedding model first

    export EMBEDDING_MODEL_NAME="CLIP/clip-vit-h-14" # Replace with your preferred model
source env.sh

    Important: You must set EMBEDDING_MODEL_NAME before running env.sh. See multimodal-embedding-serving’s Supported Models for available options.

  3. Deploy with docker compose

    docker compose -f compose_milvus.yaml up -d

It might take a while to start the services for the first time, as there are some models to be prepared.

Check if all microservices are up and runnning bash     docker compose -f compose_milvus.yaml ps    

Output

NAME                         COMMAND                  SERVICE                                 STATUS              PORTS
milvus-etcd                  "etcd -advertise-cli…"   milvus-etcd                             running (healthy)   2379-2380/tcp
milvus-minio                 "/usr/bin/docker-ent…"   milvus-minio                            running (healthy)   0.0.0.0:9000-9001->9000-9001/tcp, :::9000-9001->9000-9001/tcp
milvus-standalone            "/tini -- milvus run…"   milvus-standalone                       running (healthy)   0.0.0.0:9091->9091/tcp, 0.0.0.0:19530->19530/tcp, :::9091->9091/tcp, :::19530->19530/tcp
multimodal-embedding   gunicorn -b 0.0.0.0:8000 - ...   Up (health: starting)   0.0.0.0:9777->8000/tcp,:::9777->8000/tcp                                              
retriever-milvus             "uvicorn retriever_s…"   retriever-milvus                        running (healthy)   0.0.0.0:7770->7770/tcp, :::7770->7770/tcp

Sample curl commands#

Note: This microservice retrieves data from a Milvus database. If there is no data added into the database, the curl commands below will return collection not found. To test data retrieval, please insert some data with the Visual Data Preparation for Retrieval service first.

Basic Query#

curl -X POST http://localhost:$RETRIEVER_SERVICE_PORT/v1/retrieval \
-H "Content-Type: application/json" \
-d '{
    "query": "example query",
    "max_num_results": 5
}'

Query with Filter#

curl -X POST http://localhost:$RETRIEVER_SERVICE_PORT/v1/retrieval \
-H "Content-Type: application/json" \
-d '{
    "query": "example query",
    "filter": {
        "type": "example"
    },
    "max_num_results": 10
}'

Learn More#