Send Message
最新の更新:2024-12-22

Send Message

Send a message to the specified conversation ID and get the agent response message. Supports submitting text and/or images as message content .

Request Method

POST

Request URL

https://api.gptbots.ai/v1/conversation/message

Request Authentication

See Overview for authentication details.

Request

Example Request

curl -X POST https://api.gptbots.ai/v1/conversation/message \ -H 'Authorization: Bearer your_apikey' \ -H 'Content-Type: application/json' \ -d '{ "text": "HI!", "conversation_id": "xxxxxx", "response_mode": "streaming", "short_term_memory": true, "long_term_memory": false, "files":[ { "url": "https://res.gptbots.ai/ailab/botchat/file/38f13465ad5246190b759b3289ecba51.jpg", "name": "something.jpg", "width": 200, "height": 200 }, { "base64_content": "Your_file_base64_content", "name": "something.pdf" } ], "knowledge": { "data_ids": [ "48c70da0403cc812641b934f", "48c70da0403cc812641df35k" ] } } }'
          curl -X POST https://api.gptbots.ai/v1/conversation/message \ 
  -H 'Authorization: Bearer your_apikey' \ 
  -H 'Content-Type: application/json' \ 
  -d '{
        "text": "HI!",
        "conversation_id": "xxxxxx",
        "response_mode": "streaming",
        "short_term_memory": true,
        "long_term_memory": false,
        "files":[
          {
            "url": "https://res.gptbots.ai/ailab/botchat/file/38f13465ad5246190b759b3289ecba51.jpg",
            "name": "something.jpg",
            "width": 200,
            "height": 200
          },
          {
            "base64_content": "Your_file_base64_content", 
            "name": "something.pdf"
          }
        ],
        "knowledge": {
            "data_ids": [
                "48c70da0403cc812641b934f",
                "48c70da0403cc812641df35k"
            ]
        }
        }
}'

        
このコードブロックは、フローティングウィンドウに表示されます
Field Type Description
Authorization Bearer ${token} Use Authorization: Bearer ${token} for authentication. Get the key from the API Keys page as token.
Content-Type application/json Data type, set to application/json.

Request Body

Field Type Required Description
text string Yes Either text or files must be entered.
The user's text message, the length of the text content cannot exceed the token length limit set by the Agent configuration.
files JSON Array No text and files must have at least one input. Files are used to submit images, audio, and document-type data to the Agent. The Agent supports two file recognition schemes: "System File Recognition" and "LLM File Recognition." Different recognition schemes support different file types. Network paths for file submission are supported, with a maximum of 9 files uploaded. Documents ≤20MB, images ≤10MB, audio ≤5MB.
LLM File Recognition
  • The supported file types depend on the capabilities of each LLM. If it's a flow-agent, the intersection of all LLM-supported file types is taken.
  • System File Recognition
  • The GPTBots system recognizes uploaded files and converts them to text.
  • Document types: .pdf, .txt, .docx, .csv, .xlsx, .html, .c, .cpp, .java, .json, .md, .php, .pptx, .py, .rb, .tex, .css, .js, .ts, .xml
  • Image types: .jpg, .jpeg, .png, .gif, .webp
  • Audio types: .mp3, .wav, .acc
  • File Submission Specifications
  • base64_content, string, file stream (choose one with file URL link)
  • url, string, file URL link (choose one with file stream)
  • name, string, file name
  • width, int, image width (required for image types)
  • height, int, image height (required for image types)

  • conversation_id string Yes Conversation ID, pass in to continue previous conversation.
    response_mode string Yes blocking:
  • Blocking: wait for completion before returning result. (Long requests may be interrupted)
  • streaming: Streaming response, based on SSE (Server-Sent Events).
  • webhook: Messages from both the Agent and human customer service will be sent to the webhook address configured on the API page.
  • short_term_memory boolean No Does this message send carry short-term memory within the conversation as context? If not filled out, follow the memory settings of the Agent.
    long_term_memory boolean No Does this message send carry long-term memory within the conversation as context? If not filled out, follow the memory settings of the Agent.
    knowledge object No Customize the knowledge retrieval scope for this message. If this field does not exist, the default knowledge configuration of the Agent will be used for retrieval.
    data_ids array No data_ids is an array of knowledge document IDs.
    If this parameter is an empty array, such as "data_ids": [], it is considered as not retrieving any knowledge documents.
    If this parameter has values, retrieval will be limited to the specified knowledge document ID range.

    Response

    Example Response

    { "message_id": "65a4ccfC7ce58e728d5897e0", "message_type": "ANSWER", "text": "Hi, is there anything I can help you?", "flow_output": [ { "content": "Hello", "branch": "1", "from_component_name": "User Input" } ], "create_time": 1679587005, "conversation_id": "657303a8a764d47094874bbe" }
              {
      "message_id": "65a4ccfC7ce58e728d5897e0",
      "message_type": "ANSWER",
      "text": "Hi, is there anything I can help you?",
      "flow_output": [
        {
          "content": "Hello",
          "branch": "1", 
          "from_component_name": "User Input"
        }
      ],
      "create_time": 1679587005,
      "conversation_id": "657303a8a764d47094874bbe"
    }
    
            
    このコードブロックは、フローティングウィンドウに表示されます

    Success Response (Blocking)

    Field Type Description
    message_id string Unique message ID.
    message_type string Message type, value: ANSWER, QUESTION.
    text string Reply text.
    flow_output JSON Array flow agent reply content.
    content string flow agent component reply text.
    branch string flow agent branch.
    from_component_name string flow agent upstream component name.
    create_time long Timestamp when reply message was created.
    conversation_id string Conversation ID.

    Success Response (Streaming)

    Field Type Description
    code int Message type code, 3-Text, 10-FlowOutput, 0-End.
    message string Message type, value: Text, FlowOutput, End.
    data object Reply content.

    Streaming data is returned in multiple chunks:

    {"code":3,"message":"Text","data":"I"} {"code":3,"message":"Text","data":"can"} {"code":3,"message":"Text","data":"help"} {"code":3,"message":"Text","data":"you"} {"code":3,"message":"Text","data":"?"} {"code":10,"message":"FlowOutput","data":[{"content":"Hello","branch":null,"from_component_name":"User Input"}]} {"code":0,"message":"End","data":null}
              {"code":3,"message":"Text","data":"I"}
    {"code":3,"message":"Text","data":"can"}  
    {"code":3,"message":"Text","data":"help"}
    {"code":3,"message":"Text","data":"you"}
    {"code":3,"message":"Text","data":"?"}
    {"code":10,"message":"FlowOutput","data":[{"content":"Hello","branch":null,"from_component_name":"User Input"}]}
    {"code":0,"message":"End","data":null}
    
            
    このコードブロックは、フローティングウィンドウに表示されます

    Success Response(webhook)

    Field Type Description
    message_id string Unique message ID.
    message_type string Message type, value: ANSWER, QUESTION.
    create_time long Timestamp when reply message was created.
    conversation_id string Conversation ID.

    Failure Response

    Field Type Description
    code int Error code.
    message string Error details.

    When developers have configured the webhook address, after a successful response, the GPTBots system sends messages from both the Agent and human customer support to the webhook address. For detailed message formats, please refer to Webhook Message Reception.

    Error Codes

    Code Message
    40000 Invalid parameter
    40127 Developer authentication failed
    40356 Conversation does not exist
    50000 Internal server error
    40364 This Agent does not use an LLM that supports image mode
    20059 Agent deleted
    20040 Exceeded question limit
    40358 conversation_id does not match agent or user
    20022 Credit not enough