Multimodal CLIP Embedding Microservice¶

The Multimodal CLIP Embedding Microservice provides a powerful solution for converting textual and visual data into high-dimensional vector embeddings. These embeddings capture the semantic essence of the input, enabling robust applications in multi-modal data processing, information retrieval, recommendation systems, and more.

Start Microservice¶

Build Docker Image¶

To build the Docker image, execute the following commands:

cd ../../..
docker build -t opea/embedding:latest \
  --build-arg https_proxy=$https_proxy \
  --build-arg http_proxy=$http_proxy \
  -f comps/embeddings/src/Dockerfile .

Run Docker with Docker Compose¶

cd comps/embeddings/deployment/docker_compose/
docker compose up clip-embedding-server -d

Consume Embedding Service¶

Check Service Status¶

Verify that the embedding service is running properly by checking its health status with this command:

curl http://localhost:6000/v1/health_check \
  -X GET \
  -H 'Content-Type: application/json'

Use the Embedding Service API¶

The service supports OpenAI API-compatible requests.

Single Text Input:

curl http://localhost:6000/v1/embeddings \
  -X POST \
  -d '{"input":"Hello, world!"}' \
  -H 'Content-Type: application/json'

Multiple Texts with Parameters:

curl http://localhost:6000/v1/embeddings \
  -X POST \
  -d '{"input":["Hello, world!","How are you?"], "dimensions":100}' \
  -H 'Content-Type: application/json'