vllm-deploy/test.py

from openai import OpenAI
import base64

# API configuration
openai_api_key = "token-abc123"  # API key must match the one set when launching the service
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

# Read and encode local image
with open('/mnt/data/xiuying/Code/xywang/demo.jpeg', 'rb') as file:
    image = "data:image/jpeg;base64," + base64.b64encode(file.read()).decode('utf-8')

chat_response = client.chat.completions.create(
    model="MiniCPM-V-4-Q4_K_M.gguf",  # Specify model path or HuggingFace ID
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Please describe this image"},
            {
                "type": "image_url",
                "image_url": {
                    "url": image,  # Supports network image URLs
                },
            },
        ],
    }],
    extra_body={
        "stop_token_ids": [1, 73440]
    }
)

print("Chat response:", chat_response)
print("Chat response content:", chat_response.choices[0].message.content)