lianghsun/ollama-bge-m3-embed repository overview

⁠bge-m3 Embedding Model Powered by Ollama Framework

This repository provides a Docker image for running an API service based on the Ollama framework. The image is specifically designed for efficiently serving the bge-m3 embedding model, enabling high-performance inference on modern GPU infrastructure.

⁠Usage:

To run the container with GPU support:

docker run -d --gpus "device=0" \
-v ollama:/root/.ollama \
--network docker_default \
-p 11434:11434 \
--name embed-api \
lianghsun/ollama-bge-m3-embed

or CPU-only:

docker run -d \
-v ollama:/root/.ollama \
-p 11434:11434 \
--name embed-api \
lianghsun/ollama-bge-m3-embed

Next, use the REST API to generate vector embeddings from the model:

curl http://localhost:11434/api/embeddings -d '{
  "model": "bge-m3",
  "prompt": "Llamas are members of the camelid family"
}'

⁠Exposed Ports:

• 11434/tcp: The port where the API service is accessible.

⁠Environment Variables:

You can pass additional environment variables for further customization, such as model directories or API settings.