add support for video_url in chat.completions

Author: orangetin

README.md

@@ -57,13 +57,61 @@ from together import Together
 
 client = Together(api_key=os.environ.get("TOGETHER_API_KEY"))
 
+# Simple text message
 response = client.chat.completions.create(
     model="mistralai/Mixtral-8x7B-Instruct-v0.1",
     messages=[{"role": "user", "content": "tell me about new york"}],
 )
 print(response.choices[0].message.content)
+
+# Multi-modal message with text and image
+response = client.chat.completions.create(
+    model="meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
+    messages=[{
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's in this image?"
+            },
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://example.com/image.jpg"
+                }
+            }
+        ]
+    }]
+)
+
+# Multi-modal message with text and video
+response = client.chat.completions.create(
+    model="Qwen/Qwen2.5-VL-72B-Instruct",
+    messages=[{
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "What's happening in this video?"
+            },
+            {
+                "type": "video_url",
+                "video_url": {
+                    "url": "https://example.com/video.mp4"
+                }
+            }
+        ]
+    }]
+)
 ```
 
+The chat completions API supports three types of content:
+- Plain text messages using the `content` field directly
+- Multi-modal messages with images using `type: "image_url"`
+- Multi-modal messages with videos using `type: "video_url"`
+
+When using multi-modal content, the `content` field becomes an array of content objects, each with its own type and corresponding data.
+
 #### Streaming
 
 ```python

src/together/types/chat_completions.py

@@ -44,16 +44,22 @@ class ToolCalls(BaseModel):
 class ChatCompletionMessageContentType(str, Enum):
     TEXT = "text"
     IMAGE_URL = "image_url"
+    VIDEO_URL = "video_url"
 
 
 class ChatCompletionMessageContentImageURL(BaseModel):
     url: str
 
 
+class ChatCompletionMessageContentVideoURL(BaseModel):
+    url: str
+
+
 class ChatCompletionMessageContent(BaseModel):
     type: ChatCompletionMessageContentType
     text: str | None = None
     image_url: ChatCompletionMessageContentImageURL | None = None
+    video_url: ChatCompletionMessageContentVideoURL | None = None
 
 
 class ChatCompletionMessage(BaseModel):

tests/unit/test_video_url.py

@@ -0,0 +1,40 @@
+from together.types.chat_completions import (
+    ChatCompletionMessage,
+    ChatCompletionMessageContent,
+    ChatCompletionMessageContentType,
+    ChatCompletionMessageContentVideoURL,
+    MessageRole,
+)
+
+
+def test_video_url_message():
+    # Test creating a message with video_url content
+    message = ChatCompletionMessage(
+        role=MessageRole.USER,
+        content=[
+            ChatCompletionMessageContent(
+                type=ChatCompletionMessageContentType.TEXT, text="What's in this video?"
+            ),
+            ChatCompletionMessageContent(
+                type=ChatCompletionMessageContentType.VIDEO_URL,
+                video_url=ChatCompletionMessageContentVideoURL(
+                    url="https://example.com/video.mp4"
+                ),
+            ),
+        ],
+    )
+
+    # Verify the message structure
+    assert message.role == MessageRole.USER
+    assert isinstance(message.content, list)
+    assert len(message.content) == 2
+
+    # Verify text content
+    assert message.content[0].type == ChatCompletionMessageContentType.TEXT
+    assert message.content[0].text == "What's in this video?"
+    assert message.content[0].video_url is None
+
+    # Verify video_url content
+    assert message.content[1].type == ChatCompletionMessageContentType.VIDEO_URL
+    assert message.content[1].text is None
+    assert message.content[1].video_url.url == "https://example.com/video.mp4"