Update README.md

README.md

@@ -198,6 +198,7 @@ pip install --upgrade mistral_common
 
 You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile).
 
+#### Text understanding example
 ```py
 from vllm import LLM
 from vllm.sampling_params import SamplingParams
@@ -241,6 +242,50 @@ outputs = llm.chat(messages, sampling_params=sampling_params)
 print(outputs[0].outputs[0].text)
 ```
 
+#### Image understanding example
+```py
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
+from huggingface_hub import hf_hub_download
+from datetime import datetime, timedelta
+
+model_name = "mistralai/Pixtral-Large-Instruct-2411"
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, 'r') as file:
+        system_prompt = file.read()
+    today = datetime.today().strftime('%Y-%m-%d')
+    yesterday = (datetime.today() - timedelta(days=1)).strftime('%Y-%m-%d')
+    model_name = repo_id.split("/")[-1]
+    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
+
+SYSTEM_PROMPT = load_system_prompt(model_name, "SYSTEM_PROMPT.txt")
+
+user_prompt = "Describe this image in one sentence."
+
+image_url = "https://picsum.photos/id/237/200/300"
+
+messages = [
+    {
+        "role": "system",
+        "content": SYSTEM_PROMPT
+    },
+    {
+        "role": "user",
+        "content": [{"type": "text", "text": user_prompt}, {"type": "image_url", "image_url": {"url": image_url}}]
+    },
+]
+
+sampling_params = SamplingParams(max_tokens=128_000)
+
+# note that running this model on GPU requires over 300 GB of GPU RAM
+llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4})
+
+outputs = llm.chat(messages, sampling_params=sampling_params)
+
+print(outputs[0].outputs[0].text)
+```
 
 **_Server_**