import sglang as sgl


def main():
    # Sample prompts.
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]
    # Create an LLM.
    llm = sgl.Engine(
        model_path="Alibaba-NLP/gte-Qwen2-1.5B-instruct", is_embedding=True
    )

    outputs = llm.encode(prompts)
    # Print the outputs (embedding vectors)
    for prompt, output in zip(prompts, outputs):
        print("===============================")
        print(f"Prompt: {prompt}\nEmbedding vector: {output['embedding']}")


# The __main__ condition is necessary here because we use "spawn" to create subprocesses
# Spawn starts a fresh program every time, if there is no __main__, it will run into infinite loop to keep spawning processes from sgl.Engine
if __name__ == "__main__":
    main()