Merge pull request #3 from langgenius/feat/add-video-and-audio-prompt…

…-message

feat(entities): Add VideoPromptMessageContent and AudioPromptMessageContent

python/dify_plugin/entities/model/message.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Literal, Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, Field, field_validator
 
 
 class PromptMessageRole(Enum):
@@ -55,6 +55,8 @@ class PromptMessageContentType(Enum):
 
     TEXT = "text"
     IMAGE = "image"
+    AUDIO = "audio"
+    VIDEO = "video"
     DOCUMENT = "document"
 
 
@@ -75,6 +77,18 @@ class TextPromptMessageContent(PromptMessageContent):
     type: PromptMessageContentType = PromptMessageContentType.TEXT
 
 
+class VideoPromptMessageContent(PromptMessageContent):
+    data: str = Field(..., description="Base64 encoded video data")
+    type: PromptMessageContentType = PromptMessageContentType.VIDEO
+    format: str = Field(..., description="Video format")
+
+
+class AudioPromptMessageContent(PromptMessageContent):
+    type: PromptMessageContentType = PromptMessageContentType.AUDIO
+    data: str = Field(..., description="Base64 encoded audio data")
+    format: str = Field(..., description="Audio format")
+
+
 class ImagePromptMessageContent(PromptMessageContent):
     """
     Model class for image prompt message content.
@@ -133,6 +147,10 @@ def transform_content(cls, value: list[dict] | str | None) -> Optional[str | lis
                     result.append(ImagePromptMessageContent(**content))
                 elif content.get("type") == PromptMessageContentType.DOCUMENT.value:
                     result.append(DocumentPromptMessageContent(**content))
+                elif content.get("type") == PromptMessageContentType.AUDIO.value:
+                    result.append(AudioPromptMessageContent(**content))
+                elif content.get("type") == PromptMessageContentType.VIDEO.value:
+                    result.append(VideoPromptMessageContent(**content))
             return result