llm_vector_server/applications/config/model_config.py

LOCAL_MODEL_CONFIG = {
    "Qwen3-Embedding-0.6B": "/models/Qwen3-Embedding-0.6B",
    "Qwen3-Embedding-4B": "/models/Qwen3-Embedding-4B",
    "Qwen3-Embedding-8B": "/models/Qwen3-Embedding-8B",
}

DEFAULT_MODEL = "Qwen3-Embedding-4B"

VLLM_SERVER_URL = "http://vllm-qwen:8000/v1/embeddings"