@ -103,6 +103,16 @@ The text generation application offers non-session support and is ideal for tran
- `metadata` (object) Metadata
- `usage` (Usage) Model usage information
- `retriever_resources` (array[RetrieverResource]) Citation and Attribution List
- `event: tts_message` TTS audio stream event, that is, speech synthesis output. The content is an audio block in Mp3 format, encoded as a base64 string. When playing, simply decode the base64 and feed it into the player. (This message is available only when auto-play is enabled)
- `task_id` (string) Task ID, used for request tracking and the stop response interface below
- `message_id` (string) Unique message ID
- `audio` (string) The audio after speech synthesis, encoded in base64 text content, when playing, simply decode the base64 and feed it into the player
When output content moderation is enabled, if the content is flagged, then the message content will be replaced with a preset reply through this event.
- `task_id` (string) Task ID, used for request tracking and the below Stop Generate API
@ -185,6 +195,8 @@ The text generation application offers non-session support and is ideal for tran
For text messages generated by Dify, simply pass the generated message-id directly. The backend will use the message-id to look up the corresponding content and synthesize the voice information directly. If both message_id and text are provided simultaneously, the message_id is given priority.
</Property>
<Property name='text' type='str' key='text'>
Speech generated content。
</Property>
<Property name='user' type='string' key='user'>
The user identifier, defined by the developer, must ensure uniqueness within the app.
@ -118,6 +118,16 @@ Chat applications support session persistence, allowing previous chat history to
- `metadata` (object) Metadata
- `usage` (Usage) Model usage information
- `retriever_resources` (array[RetrieverResource]) Citation and Attribution List
- `event: tts_message` TTS audio stream event, that is, speech synthesis output. The content is an audio block in Mp3 format, encoded as a base64 string. When playing, simply decode the base64 and feed it into the player. (This message is available only when auto-play is enabled)
- `task_id` (string) Task ID, used for request tracking and the stop response interface below
- `message_id` (string) Unique message ID
- `audio` (string) The audio after speech synthesis, encoded in base64 text content, when playing, simply decode the base64 and feed it into the player
When output content moderation is enabled, if the content is flagged, then the message content will be replaced with a preset reply through this event.
- `task_id` (string) Task ID, used for request tracking and the below Stop Generate API
@ -276,6 +286,8 @@ Chat applications support session persistence, allowing previous chat history to
For text messages generated by Dify, simply pass the generated message-id directly. The backend will use the message-id to look up the corresponding content and synthesize the voice information directly. If both message_id and text are provided simultaneously, the message_id is given priority.
</Property>
<Property name='text' type='str' key='text'>
Speech generated content。
</Property>
<Property name='user' type='string' key='user'>
The user identifier, defined by the developer, must ensure uniqueness within the app.
- `event: tts_message` TTS audio stream event, that is, speech synthesis output. The content is an audio block in Mp3 format, encoded as a base64 string. When playing, simply decode the base64 and feed it into the player. (This message is available only when auto-play is enabled)
- `task_id` (string) Task ID, used for request tracking and the stop response interface below
- `message_id` (string) Unique message ID
- `audio` (string) The audio after speech synthesis, encoded in base64 text content, when playing, simply decode the base64 and feed it into the player
For text messages generated by Dify, simply pass the generated message-id directly. The backend will use the message-id to look up the corresponding content and synthesize the voice information directly. If both message_id and text are provided simultaneously, the message_id is given priority.
</Property>
<Property name='text' type='str' key='text'>
Speech generated content。
</Property>
<Property name='user' type='string' key='user'>
The user identifier, defined by the developer, must ensure uniqueness within the app.
data: {"event": "agent_thought", "id": "67a99dc1-4f82-42d3-b354-18d4594840c8", "task_id": "9cf1ddd7-f94b-459b-b942-b77b26c59e9b", "message_id": "1fb10045-55fd-4040-99e6-d048d07cbad3", "position": 2, "thought": "I have created an image of a cute Japanese anime girl with white hair and blue eyes wearing a bunny girl suit.", "observation": "", "tool": "", "tool_input": "", "created_at": 1705639511, "message_files": [], "conversation_id": "c216c595-2d89-438c-b33c-aae5ddddd142"}
@ -147,6 +147,16 @@ Workflow applications offers non-session support and is ideal for translation, a
- `total_steps` (int) default 0
- `created_at` (timestamp) start time
- `finished_at` (timestamp) end time
- `event: tts_message` TTS audio stream event, that is, speech synthesis output. The content is an audio block in Mp3 format, encoded as a base64 string. When playing, simply decode the base64 and feed it into the player. (This message is available only when auto-play is enabled)
- `task_id` (string) Task ID, used for request tracking and the stop response interface below
- `message_id` (string) Unique message ID
- `audio` (string) The audio after speech synthesis, encoded in base64 text content, when playing, simply decode the base64 and feed it into the player
chenxu9741
2 years ago
committed by
GitHub