[Doc] Add video example to openai client for multimodal (#11521)

Signed-off-by: Isotr0py <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>

Author: Isotr0py

docs/source/usage/multimodal_inputs.md

@@ -294,12 +294,58 @@ $ export VLLM_IMAGE_FETCH_TIMEOUT=<timeout>
 
 ### Video
 
-Instead of {code}`image_url`, you can pass a video file via {code}`video_url`.
+Instead of {code}`image_url`, you can pass a video file via {code}`video_url`. Here is a simple example using [LLaVA-OneVision](https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-ov-hf).
 
-You can use [these tests](gh-file:entrypoints/openai/test_video.py) as reference.
+First, launch the OpenAI-compatible server:
+
+```bash
+vllm serve llava-hf/llava-onevision-qwen2-0.5b-ov-hf --task generate --max-model-len 8192
+```
+
+Then, you can use the OpenAI client as follows:
+```python
+from openai import OpenAI
+
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+video_url = "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerFun.mp4"
+
+## Use video url in the payload
+chat_completion_from_url = client.chat.completions.create(
+    messages=[{
+        "role":
+        "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this video?"
+            },
+            {
+                "type": "video_url",
+                "video_url": {
+                    "url": video_url
+                },
+            },
+        ],
+    }],
+    model=model,
+    max_completion_tokens=64,
+)
+
+result = chat_completion_from_url.choices[0].message.content
+print("Chat completion output from image url:", result)
+```
+
+Full example: <gh-file:examples/openai_chat_completion_client_for_multimodal.py>
 
 ````{note}
-By default, the timeout for fetching videos through HTTP URL url is `30` seconds.
+By default, the timeout for fetching videos through HTTP URL is `30` seconds.
 You can override this by setting the environment variable:
 
 ```console

examples/openai_chat_completion_client_for_multimodal.py

@@ -18,7 +18,6 @@
 import requests
 from openai import OpenAI
 
-from vllm.assets.audio import AudioAsset
 from vllm.utils import FlexibleArgumentParser
 
 # Modify OpenAI's API key and API base to use vLLM's API server.
@@ -151,8 +150,66 @@ def run_multi_image() -> None:
     print("Chat completion output:", result)
 
 
+# Video input inference
+def run_video() -> None:
+    video_url = "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerFun.mp4"
+    video_base64 = encode_base64_content_from_url(video_url)
+
+    ## Use video url in the payload
+    chat_completion_from_url = client.chat.completions.create(
+        messages=[{
+            "role":
+            "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "What's in this video?"
+                },
+                {
+                    "type": "video_url",
+                    "video_url": {
+                        "url": video_url
+                    },
+                },
+            ],
+        }],
+        model=model,
+        max_completion_tokens=64,
+    )
+
+    result = chat_completion_from_url.choices[0].message.content
+    print("Chat completion output from image url:", result)
+
+    ## Use base64 encoded video in the payload
+    chat_completion_from_base64 = client.chat.completions.create(
+        messages=[{
+            "role":
+            "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "What's in this video?"
+                },
+                {
+                    "type": "video_url",
+                    "video_url": {
+                        "url": f"data:video/mp4;base64,{video_base64}"
+                    },
+                },
+            ],
+        }],
+        model=model,
+        max_completion_tokens=64,
+    )
+
+    result = chat_completion_from_base64.choices[0].message.content
+    print("Chat completion output from base64 encoded image:", result)
+
+
 # Audio input inference
 def run_audio() -> None:
+    from vllm.assets.audio import AudioAsset
+
     audio_url = AudioAsset("winning_call").url
     audio_base64 = encode_base64_content_from_url(audio_url)
 
@@ -240,6 +297,7 @@ def run_audio() -> None:
     "text-only": run_text_only,
     "single-image": run_single_image,
     "multi-image": run_multi_image,
+    "video": run_video,
     "audio": run_audio,
 }
 
@@ -253,12 +311,11 @@ def main(args) -> None:
     parser = FlexibleArgumentParser(
         description='Demo on using OpenAI client for online inference with '
         'multimodal language models served with vLLM.')
-    parser.add_argument(
-        '--chat-type',
-        '-c',
-        type=str,
-        default="single-image",
-        choices=["text-only", "single-image", "multi-image", "audio"],
-        help='Conversation type with multimodal data.')
+    parser.add_argument('--chat-type',
+                        '-c',
+                        type=str,
+                        default="single-image",
+                        choices=list(example_function_map.keys()),
+                        help='Conversation type with multimodal data.')
     args = parser.parse_args()
     main(args)