incorrect response structure in openapi documentation of app

realethanhsu commented 2 months ago

Self Checks

[X] This is only for bug report, if you would like to ask a question, please head to Discussions.
[X] I have searched for existing issues search for existing issues, including closed ones.
[X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
[X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
[X] Please do not modify this template :) and fill in all the required fields.

Dify version

0.7.1

Cloud or Self Hosted

Self Hosted (Source)

Steps to reproduce

On the application’s accessible API page, review the example of the streamed message response structure for the /chat-messages endpoint.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

dosubot[bot] commented 2 months ago

@ethan-fly Hello there! I'm here to help you with bugs, questions, and becoming a contributor. Let's tackle this together while we wait for a human maintainer.

To correct the response structure in the OpenAPI documentation of the app for the /chat-messages endpoint in version 0.7.1, you need to ensure that the response format is clearly defined and matches the expected output. Here is the corrected response structure:

Response

When response_mode is blocking, return a ChatCompletionResponse object. When response_mode is streaming, return a ChunkCompletionResponse stream.

ChatCompletionResponse

Returns the complete App result, Content-Type is application/json.

message_id (string): Unique message ID
conversation_id (string): Conversation ID
mode (string): App mode, fixed as chat
answer (string): Complete response content
metadata (object): Metadata
- usage (Usage): Model usage information
- retriever_resources (array[RetrieverResource]): Citation and Attribution List
created_at (int): Message creation timestamp, e.g., 1705395332

Example Response for Blocking Mode

{
    "event": "message",
    "message_id": "9da23599-e713-473b-982c-4328d4f5c78a",
    "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2",
    "mode": "chat",
    "answer": "iPhone 13 Pro Max specs are listed here:...",
    "metadata": {
        "usage": {
            "prompt_tokens": 1033,
            "prompt_unit_price": "0.001",
            "prompt_price_unit": "0.001",
            "prompt_price": "0.0010330",
            "completion_tokens": 128,
            "completion_unit_price": "0.002",
            "completion_price_unit": "0.001",
            "completion_price": "0.0002560",
            "total_tokens": 1161,
            "total_price": "0.0012890",
            "currency": "USD",
            "latency": 0.7682376249867957
        },
        "retriever_resources": [
            {
                "position": 1,
                "dataset_id": "101b4c97-fc2e-463c-90b1-5261a4cdcafb",
                "dataset_name": "iPhone",
                "document_id": "8dd1ad74-0b5f-4175-b735-7d98bbbb4e00",
                "document_name": "iPhone List",
                "segment_id": "ed599c7f-2766-4294-9d1d-e5235a61270a",
                "score": 0.98457545,
                "content": "\"Model\",\"Release Date\",\"Display Size\",\"Resolution\",\"Processor\",\"RAM\",\"Storage\",\"Camera\",\"Battery\",\"Operating System\"\n\"iPhone 13 Pro Max\",\"September 24, 2021\",\"6.7 inch\",\"1284 x 2778\",\"Hexa-core (2x3.23 GHz Avalanche + 4x1.82 GHz Blizzard)\",\"6 GB\",\"128, 256, 512 GB, 1TB\",\"12 MP\",\"4352 mAh\",\"iOS 15\""
            }
        ]
    },
    "created_at": 1705407629
}

Example Response for Streaming Mode

data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " I", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": "'m", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " glad", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " to", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " meet", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " you", "created_at": 1679586595}

For more detailed information on how to use the API, including example requests, you can refer to the API documentation provided by Dify in the Applications -> Access API section. This documentation includes sample calls for both text-generation and conversational applications, which can help you understand how to structure your requests and handle responses effectively. The ChatMessageApi class in the api/controllers/console/app/completion.py file handles the /chat-messages endpoint and ensures the response structure is correctly implemented ^[1]^[2]^[3]^[4].

To continue talking to Dosu, mention @dosu.

dosubot[bot] commented 2 months ago

@ethan-fly Hello there! I'm here to help you with bugs, questions, and becoming a contributor. Let's tackle this together while we wait for a human maintainer.

To correct the response structure in the OpenAPI documentation of the app for the /chat-messages endpoint in version 0.7.1, you need to ensure that the response format is clearly defined and matches the expected output. Here is the corrected response structure:

Response

When response_mode is blocking, return a ChatCompletionResponse object. When response_mode is streaming, return a ChunkCompletionResponse stream.

ChatCompletionResponse

Returns the complete App result, Content-Type is application/json.

message_id (string): Unique message ID
conversation_id (string): Conversation ID
mode (string): App mode, fixed as chat
answer (string): Complete response content
metadata (object): Metadata
- usage (Usage): Model usage information
- retriever_resources (array[RetrieverResource]): Citation and Attribution List
created_at (int): Message creation timestamp, e.g., 1705395332

Example Response for Blocking Mode

{
    "event": "message",
    "message_id": "9da23599-e713-473b-982c-4328d4f5c78a",
    "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2",
    "mode": "chat",
    "answer": "iPhone 13 Pro Max specs are listed here:...",
    "metadata": {
        "usage": {
            "prompt_tokens": 1033,
            "prompt_unit_price": "0.001",
            "prompt_price_unit": "0.001",
            "prompt_price": "0.0010330",
            "completion_tokens": 128,
            "completion_unit_price": "0.002",
            "completion_price_unit": "0.001",
            "completion_price": "0.0002560",
            "total_tokens": 1161,
            "total_price": "0.0012890",
            "currency": "USD",
            "latency": 0.7682376249867957
        },
        "retriever_resources": [
            {
                "position": 1,
                "dataset_id": "101b4c97-fc2e-463c-90b1-5261a4cdcafb",
                "dataset_name": "iPhone",
                "document_id": "8dd1ad74-0b5f-4175-b735-7d98bbbb4e00",
                "document_name": "iPhone List",
                "segment_id": "ed599c7f-2766-4294-9d1d-e5235a61270a",
                "score": 0.98457545,
                "content": "\"Model\",\"Release Date\",\"Display Size\",\"Resolution\",\"Processor\",\"RAM\",\"Storage\",\"Camera\",\"Battery\",\"Operating System\"\n\"iPhone 13 Pro Max\",\"September 24, 2021\",\"6.7 inch\",\"1284 x 2778\",\"Hexa-core (2x3.23 GHz Avalanche + 4x1.82 GHz Blizzard)\",\"6 GB\",\"128, 256, 512 GB, 1TB\",\"12 MP\",\"4352 mAh\",\"iOS 15\""
            }
        ]
    },
    "created_at": 1705407629
}

Example Response for Streaming Mode

data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " I", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": "'m", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " glad", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " to", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " meet", "created_at": 1679586595}
data: {"event": "message", "message_id": "5ad4cb98-f0c7-4085-b384-88c403be6290", "conversation_id": "45701982-8118-4bc5-8e9b-64562b4555f2", "answer": " you", "created_at": 1679586595}

For more detailed information on how to use the API, including example requests, you can refer to the API documentation provided by Dify in the Applications -> Access API section. This documentation includes sample calls for both text-generation and conversational applications, which can help you understand how to structure your requests and handle responses effectively. The ChatMessageApi class in the api/controllers/console/app/completion.py file handles the /chat-messages endpoint and ensures the response structure is correctly implemented ^[1]^[2]^[3]^[4].

To continue talking to Dosu, mention @dosu.

langgenius / dify