How to Get AppId

You can find the AppId in your application details URL.

Start a Conversation

Authenticate with an API Key. When calling chat/completions, passing appId in the request body is recommended.
For OpenAI SDK compatibility, Authorization: Bearer <apiKey>-<appId> is also supported. The suffix is only a transport compatibility format and is not stored.
To proxy a team member identity through authProxy, the team owner must enable authProxy when creating or editing the key. The proxied member must still have permission to access the target app and chat.
Some packages require adding v1 to the BaseUrl. If you get a 404 error, try adding v1 and retry.

Start Chat

The v1 chat API is compatible with the GPT interface! If you're using the standard GPT official API, you can access FastGPT by simply changing the BaseUrl and Authorization. However, note these rules:

Parameters like model and temperature are ignored. These values are determined by your workflow configuration.
Won't return actual Token consumed. If needed, set detail=true and manually calculate tokens from responseData.

Request

bash

curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer fastgpt-xxxxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
"appId": "your_app_id",
"chatId": "my_chatId",
"stream": false,
"detail": false,
"responseChatItemId": "my_responseChatItemId",
"variables": {
    "uid": "asdfadsfasfd2323",
    "name": "张三"
},
"messages": [
    {
        "role": "user",
        "content": "导演是谁"
    }
]
}'

</Tab> <Tab value="Image/File Request Example">

Only messages differs slightly; other parameters are the same.
Direct file uploads are not supported. Upload files to your object storage and provide the URL.

bash

curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer fastgpt-xxxxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "your_app_id",
    "chatId": "abcd",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "导演是谁"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "图片链接"
                    }
                },
                {
                    "type": "file_url",
                    "name": "文件名",
                    "url": "文档链接，支持 txt md html word pdf ppt csv excel"
                }
            ]
        }
    ]
}'

</Tab> <Tab value="Parameters">

headers.Authorization: Bearer [apikey]
chatId: string | undefined.
- Empty or omitted: FastGPT context is not used, and context is built entirely from messages.
- Non-empty string: uses chatId for the chat, automatically reads messages from the FastGPT session, and uses only the last item in messages as the user question. Other messages are ignored. Make sure chatId is unique and shorter than 250 characters.
messages: Same structure as GPT chat messages.
responseChatItemId: string | undefined. If provided, FastGPT uses it as the response message ID and stores it in the database. Make sure it is unique under the current chatId.
detail: Whether to return intermediate values. In stream mode, they are separated by event; in non-stream mode, they are stored in responseData.
variables: Module variables. This object replaces [key] placeholders in input fields.

</Tab> </Tabs>

Response

json

{
  "id": "adsfasf",
  "model": "",
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "电影《铃芽之旅》的导演是新海诚。"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ]
}

</Tab> <Tab value="detail=false, stream=true Response">

bash

data: {"id":"","object":"","created":0,"choices":[{"delta":{"content":""},"index":0,"finish_reason":null}]}

data: {"id":"","object":"","created":0,"choices":[{"delta":{"content":"电"},"index":0,"finish_reason":null}]}

data: {"id":"","object":"","created":0,"choices":[{"delta":{"content":"影"},"index":0,"finish_reason":null}]}

data: {"id":"","object":"","created":0,"choices":[{"delta":{"content":"《"},"index":0,"finish_reason":null}]}

</Tab> <Tab value="detail=true, stream=false Response">

json

{
  "responseData": [
    // 不同模块的响应值, 不同版本具体值可能有差异，可先 log 自行查看最新值。
    {
      "moduleName": "Dataset Search",
      "price": 1.2000000000000002,
      "model": "Embedding-2",
      "tokens": 6,
      "similarity": 0.61,
      "limit": 3
    },
    {
      "moduleName": "AI Chat",
      "price": 454.5,
      "model": "FastAI-4k",
      "tokens": 303,
      "question": "导演是谁",
      "answer": "电影《铃芽之旅》的导演是新海诚。",
      "maxToken": 2050,
      "quoteList": [
        {
          "dataset_id": "646627f4f7b896cfd8910e38",
          "id": "8099",
          "q": "本作的主人公是谁？",
          "a": "本作的主人公是名叫铃芽的少女。",
          "source": "手动修改"
        },
        {
          "dataset_id": "646627f4f7b896cfd8910e38",
          "id": "8686",
          "q": "电影《铃芽之旅》男主角是谁？",
          "a": "电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。",
          "source": ""
        },
        {
          "dataset_id": "646627f4f7b896cfd8910e38",
          "id": "19339",
          "q": "电影《铃芽之旅》的导演是谁？22",
          "a": "电影《铃芽之旅》的导演是新海诚。",
          "source": "手动修改"
        }
      ],
      "completeMessages": [
        {
          "obj": "System",
          "value": "下面是知识库内容:\n1. [本作的主人公是谁？\n本作的主人公是名叫铃芽的少女。]\n2. [电影《铃芽之旅》男主角是谁？\n电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。]\n3. [电影《铃芽之旅》的导演是谁？22\n电影《铃芽之旅》的导演是新海诚。]\n"
        },
        {
          "obj": "System",
          "value": "1.请记住，你的身份是百度的下一代知识增强语言模型，能够完全根据知识库提供的内容回答问题。\n\n2. 你忘记了关于电影《铃芽之旅》以外的内容。"
        },
        {
          "obj": "System",
          "value": "你仅回答关于电影《玲芽之旅》的问题，其余问题直接回复: 我不清楚。"
        },
        {
          "obj": "Human",
          "value": "导演是谁"
        },
        {
          "obj": "AI",
          "value": "电影《铃芽之旅》的导演是新海诚。"
        }
      ]
    }
  ],
  "id": "",
  "model": "",
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "电影《铃芽之旅》的导演是新海诚。"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ]
}

</Tab> <Tab value="detail=true, stream=true Response">

bash

event: flowNodeStatus
data: {"status":"running","name":"知识库搜索"}

event: flowNodeStatus
data: {"status":"running","name":"AI 对话"}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"content":"电影"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"content":"《铃"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"content":"芽之旅》"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"content":"的导演是新"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"content":"海诚。"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{},"index":0,"finish_reason":"stop"}]}

event: answer
data: [DONE]

event: flowResponses
data: [{"moduleName":"知识库搜索","moduleType":"datasetSearchNode","runningTime":1.78},{"question":"导演是谁","quoteList":[{"id":"654f2e49b64caef1d9431e8b","q":"电影《铃芽之旅》的导演是谁？","a":"电影《铃芽之旅》的导演是新海诚!","indexes":[{"type":"qa","dataId":"3515487","text":"电影《铃芽之旅》的导演是谁？","_id":"654f2e49b64caef1d9431e8c","defaultIndex":true}],"datasetId":"646627f4f7b896cfd8910e38","collectionId":"653279b16cd42ab509e766e8","sourceName":"data (81).csv","sourceId":"64fd3b6423aa1307b65896f6","score":0.8935586214065552},{"id":"6552e14c50f4a2a8e632af11","q":"导演是谁？","a":"电影《铃芽之旅》的导演是新海诚。","indexes":[{"defaultIndex":true,"type":"qa","dataId":"3644565","text":"导演是谁？\n电影《铃芽之旅》的导演是新海诚。","_id":"6552e14dde5cc7ba3954e417"}],"datasetId":"646627f4f7b896cfd8910e38","collectionId":"653279b16cd42ab509e766e8","sourceName":"data (81).csv","sourceId":"64fd3b6423aa1307b65896f6","score":0.8890955448150635},{"id":"654f34a0b64caef1d946337e","q":"本作的主人公是谁？","a":"本作的主人公是名叫铃芽的少女。","indexes":[{"type":"qa","dataId":"3515541","text":"本作的主人公是谁？","_id":"654f34a0b64caef1d946337f","defaultIndex":true}],"datasetId":"646627f4f7b896cfd8910e38","collectionId":"653279b16cd42ab509e766e8","sourceName":"data (81).csv","sourceId":"64fd3b6423aa1307b65896f6","score":0.8738770484924316},{"id":"654f3002b64caef1d944207a","q":"电影《铃芽之旅》男主角是谁？","a":"电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。","indexes":[{"type":"qa","dataId":"3515538","text":"电影《铃芽之旅》男主角是谁？","_id":"654f3002b64caef1d944207b","defaultIndex":true}],"datasetId":"646627f4f7b896cfd8910e38","collectionId":"653279b16cd42ab509e766e8","sourceName":"data (81).csv","sourceId":"64fd3b6423aa1307b65896f6","score":0.8607980012893677},{"id":"654f2fc8b64caef1d943fd46","q":"电影《铃芽之旅》的编剧是谁？","a":"新海诚是本片的编剧。","indexes":[{"defaultIndex":true,"type":"qa","dataId":"3515550","text":"电影《铃芽之旅》的编剧是谁？22","_id":"654f2fc8b64caef1d943fd47"}],"datasetId":"646627f4f7b896cfd8910e38","collectionId":"653279b16cd42ab509e766e8","sourceName":"data (81).csv","sourceId":"64fd3b6423aa1307b65896f6","score":0.8468944430351257}],"moduleName":"AI 对话","moduleType":"chatNode","runningTime":1.86}]

</Tab> <Tab value="Event Values">

event取值：

- answer: 返回给客户端的文本（最终会算作回答）
- fastAnswer: 指定回复返回给客户端的文本（最终会算作回答）
- toolCall: 执行工具
- toolParams: 工具参数
- toolResponse: 工具返回
- flowNodeStatus: 运行到的节点状态
- flowResponses: 节点完整响应
- updateVariables: 更新变量
- error: 报错

</Tab> </Tabs>

Response

If your workflow contains interactive nodes, still call this API with detail=true. Get interactive node config from event=interactive data. For stream=false, find type=interactive elements in choices.

When calling a workflow with interactive nodes, if an interactive node is encountered, it returns immediately with this info:

json

{
  "interactive": {
    "type": "userSelect",
    "params": {
      "description": "测试",
      "userSelectOptions": [
        {
          "value": "Confirm",
          "key": "option1"
        },
        {
          "value": "Cancel",
          "key": "option2"
        }
      ]
    }
  }
}

</Tab> <Tab value="Form Input">

json

{
  "interactive": {
    "type": "userInput",
    "params": {
      "description": "测试",
      "inputForm": [
        {
          "type": "input",
          "key": "测试 1",
          "label": "测试 1",
          "description": "",
          "value": "",
          "defaultValue": "",
          "valueType": "string",
          "required": false,
          "list": [
            {
              "label": "",
              "value": ""
            }
          ]
        },
        {
          "type": "numberInput",
          "key": "测试 2",
          "label": "测试 2",
          "description": "",
          "value": "",
          "defaultValue": "",
          "valueType": "number",
          "required": false,
          "list": [
            {
              "label": "",
              "value": ""
            }
          ]
        }
      ]
    }
  }
}

</Tab> </Tabs>

Continue Interactive Node

After receiving interactive node info, render your UI to guide user input or selection. Then call this API again to continue the workflow. Use this format:

For user selection, simply pass the selected value to messages.

bash

curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer fastgpt-xxx' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "your_app_id",
    "stream": true,
    "detail": true,
    "chatId":"22222231",
    "messages": [
        {
            "role": "user",
            "content": "Confirm"
        }
    ]
}'

</Tab> <Tab value="Form Input">

Form input is slightly more complex. Serialize the input as a JSON string for messages. Object keys match form keys, values are user inputs. Ensure chatId is consistent.

bash

curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer fastgpt-xxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "your_app_id",
    "stream": true,
    "detail": true,
    "chatId":"22231",
    "messages": [
        {
            "role": "user",
            "content": "{\"测试 1\":\"这是输入框的内容\",\"测试 2\":666}"
        }
    ]
}'

</Tab> </Tabs>

Request Plugin

Plugin API is identical to chat API, with slight parameter differences:

调用插件Type的应用时，接口默认为detail模式。
No need to pass chatId since plugins run only once.
No need to pass messages.
Pass variables to represent plugin inputs.
Get plugin outputs from pluginData.

Request

bash

curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer test-xxxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "your_app_id",
    "stream": false,
    "chatId": "test",
    "variables": {
        "query":"你好" # 我的插件输入有一个参数，变量名叫 query
    }
}'

Response

Find plugin output by locating moduleType=pluginOutput in responseData. Its pluginOutput contains the output.
Stream output is still available via choices.

json

{
  "responseData": [
    {
      "nodeId": "fdDgXQ6SYn8v",
      "moduleName": "AI 对话",
      "moduleType": "chatNode",
      "totalPoints": 0.685,
      "model": "FastAI-3.5",
      "tokens": 685,
      "query": "你好",
      "maxToken": 2000,
      "historyPreview": [
        {
          "obj": "Human",
          "value": "你好"
        },
        {
          "obj": "AI",
          "value": "你好！有什么可以帮助你的吗？欢迎向我提问。"
        }
      ],
      "contextTotalLen": 14,
      "runningTime": 1.73
    },
    {
      "nodeId": "pluginOutput",
      "moduleName": "插件输出",
      "moduleType": "pluginOutput",
      "totalPoints": 0,
      "pluginOutput": {
        "result": "你好！有什么可以帮助你的吗？欢迎向我提问。"
      },
      "runningTime": 0
    }
  ],
  "newVariables": {
    "query": "你好"
  },
  "id": "safsafsa",
  "model": "",
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "你好！有什么可以帮助你的吗？欢迎向我提问。"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ]
}

</Tab> <Tab value="detail=true, stream=true Response">

Get plugin output by deserializing the event=flowResponses string into an array. Find moduleType=pluginOutput element; its pluginOutput contains the output.
Stream output works the same as chat API.

bash

event: flowNodeStatus
data: {"status":"running","name":"AI 对话"}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":""},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"你"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"好"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"！"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"有"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"什"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"么"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"可以"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"帮"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"助"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"你"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"的"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"吗"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"？"},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":""},"index":0,"finish_reason":null}]}

event: answer
data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{},"index":0,"finish_reason":"stop"}]}

event: answer
data: [DONE]

event: flowResponses
data: [{"nodeId":"fdDgXQ6SYn8v","moduleName":"AI 对话","moduleType":"chatNode","totalPoints":0.033,"model":"FastAI-3.5","tokens":33,"query":"你好","maxToken":2000,"historyPreview":[{"obj":"Human","value":"你好"},{"obj":"AI","value":"你好！有什么可以帮助你的吗？"}],"contextTotalLen":2,"runningTime":1.42},{"nodeId":"pluginOutput","moduleName":"插件输出","moduleType":"pluginOutput","totalPoints":0,"pluginOutput":{"result":"你好！有什么可以帮助你的吗？"},"runningTime":0}]

</Tab> <Tab value="Output Retrieval">

event取值：

- answer: 返回给客户端的文本（最终会算作回答）
- fastAnswer: 指定回复返回给客户端的文本（最终会算作回答）
- toolCall: 执行工具
- toolParams: 工具参数
- toolResponse: 工具返回
- flowNodeStatus: 运行到的节点状态
- flowResponses: 节点完整响应
- updateVariables: 更新变量
- error: 报错

</Tab> </Tabs>

Chat CRUD

The following APIs can be called with any API Key.
4.8.12 and above

**Important Fields**

chatId - The ID of a session under an application
dataId - The ID of a message under a session

Session Management

Get Session List

bash

curl --location --request POST 'http://localhost:3000/api/core/chat/history/getHistories' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "offset": 0,
    "pageSize": 20,
    "source": "api"
}'

</Tab> <Tab value="Parameters">

appId - Application ID
offset - Offset (starting position)
pageSize - Number of items
source - Chat source. source=api means get API-created sessions only (excludes web UI sessions)

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": {
    "list": [
      {
        "chatId": "usdAP1GbzSGu",
        "updateTime": "2024-10-13T03:29:05.779Z",
        "appId": "66e29b870b24ce35330c0f08",
        "customTitle": "",
        "title": "你好",
        "top": false
      },
      {
        "chatId": "lC0uTAsyNBlZ",
        "updateTime": "2024-10-13T03:22:19.950Z",
        "appId": "66e29b870b24ce35330c0f08",
        "customTitle": "",
        "title": "测试",
        "top": false
      }
    ],
    "total": 2
  }
}

</Tab> </Tabs>

Update Session Title

bash

curl --location --request PUT 'http://localhost:3000/api/core/chat/history/updateHistory' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "customTitle": "自定义标题"
}'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
customTitle - Custom session title

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Update Session Pin Status

bash

curl --location --request PUT 'http://localhost:3000/api/core/chat/history/updateHistory' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "top": true
}'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
top - Whether to pin. true = pin, false = unpin

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Delete a Session

bash

curl --location --request DELETE 'http://localhost:3000/api/core/chat/history/delHistory?chatId=[chatId]&appId=[appId]' \
--header 'Authorization: Bearer [apikey]'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Clear App Sessions

Only clears sessions created via API Key. Does not clear sessions from web UI, share links, or other sources.

bash

curl --location --request DELETE 'http://localhost:3000/api/core/chat/history/clearHistories?appId=[appId]' \
--header 'Authorization: Bearer [apikey]'

</Tab> <Tab value="Parameters" >

appId - Application ID

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Message Management

Operations on messages under a specific session.

Get Session Basic Info

bash

curl --location --request GET 'http://localhost:3000/api/core/chat/init?appId=[appId]&chatId=[chatId]' \
--header 'Authorization: Bearer [apikey]'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID

</Tab> <Tab value="Response Example">

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": {
    "chatId": "sPVOuEohjo3w",
    "appId": "66e29b870b24ce35330c0f08",
    "variables": {},
    "app": {
      "chatConfig": {
        "questionGuide": true,
        "ttsConfig": {
          "type": "web"
        },
        "whisperConfig": {
          "open": false,
          "autoSend": false,
          "autoTTSResponse": false
        },
        "chatInputGuide": {
          "open": false,
          "textList": [],
          "customUrl": ""
        },
        "instruction": "",
        "variables": [],
        "fileSelectConfig": {
          "canSelectFile": true,
          "canSelectImg": true,
          "maxFiles": 10
        },
        "_id": "66f1139aaab9ddaf1b5c596d",
        "welcomeText": ""
      },
      "chatModels": ["GPT-4o-mini"],
      "name": "测试",
      "avatar": "/imgs/app/avatar/workflow.svg",
      "intro": "",
      "type": "advanced",
      "pluginInputs": []
    }
  }
}

</Tab> </Tabs>

Get Message List

bash

curl --location --request POST 'http://localhost:3000/api/core/chat/record/getPaginationRecords' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "offset": 0,
    "pageSize": 10,
    "loadCustomFeedbacks": true
}'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
offset - Offset
pageSize - Number of items
loadCustomFeedbacks - Whether to load custom feedbacks (optional)

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": {
    "list": [
      {
        "_id": "670b84e6796057dda04b0fd2",
        "dataId": "jzqdV4Ap1u004rhd2WW8yGLn",
        "obj": "Human",
        "value": [
          {
            "text": {
              "content": "你好"
            }
          }
        ],
        "customFeedbacks": []
      },
      {
        "_id": "670b84e6796057dda04b0fd3",
        "dataId": "x9KQWcK9MApGdDQH7z7bocw1",
        "obj": "AI",
        "value": [
          {
            "text": {
              "content": "你好！有什么我可以帮助你的吗？"
            }
          }
        ],
        "customFeedbacks": [],
        "totalQuoteList": [],
        "totalRunningTime": 2.42,
        "useAgentSandbox": false
      }
    ],
    "total": 2
  }
}

</Tab> </Tabs>

Get Message Run Details

bash

curl --location --request GET 'http://localhost:3000/api/core/chat/record/getResData?appId=[appId]&chatId=[chatId]&dataId=[dataId]' \
--header 'Authorization: Bearer [apikey]'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
dataId - Message ID

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": [
    {
      "id": "mVlxkz8NfyfU",
      "nodeId": "448745",
      "moduleName": "common:core.module.template.work_start",
      "moduleType": "workflowStart",
      "runningTime": 0
    },
    {
      "id": "b3FndAdHSobY",
      "nodeId": "z04w8JXSYjl3",
      "moduleName": "AI 对话",
      "moduleType": "chatNode",
      "runningTime": 1.22,
      "totalPoints": 0.02475,
      "model": "GPT-4o-mini",
      "tokens": 75,
      "query": "测试",
      "maxToken": 2000,
      "historyPreview": [
        {
          "obj": "Human",
          "value": "你好"
        },
        {
          "obj": "AI",
          "value": "你好！有什么我可以帮助你的吗？"
        },
        {
          "obj": "Human",
          "value": "测试"
        },
        {
          "obj": "AI",
          "value": "测试成功！请问你有什么具体的问题或者需要讨论的话题吗？"
        }
      ],
      "contextTotalLen": 4
    }
  ]
}

</Tab> </Tabs>

Delete Message

bash

curl --location --request DELETE 'http://localhost:3000/api/core/chat/record/delete?contentId=[contentId]&chatId=[chatId]&appId=[appId]' \
--header 'Authorization: Bearer [apikey]'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
contentId - Message ID

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Update Feedback (Like / Dislike)

Like / unlike:

bash

curl --location --request POST 'http://localhost:3000/api/core/chat/feedback/updateUserFeedback' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "dataId": "dataId",
    "userGoodFeedback": "yes"
}'

Dislike / remove dislike:

bash

curl --location --request POST 'http://localhost:3000/api/core/chat/feedback/updateUserFeedback' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "dataId": "dataId",
    "userBadFeedback": "yes"
}'

</Tab> <Tab value="Parameters" >

appId - Application ID
chatId - Session ID
dataId - Message ID
userGoodFeedback - User feedback when liking (optional). Omit to unlike.
userBadFeedback - User feedback when disliking (optional). Omit to remove dislike.

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": null
}

</Tab> </Tabs>

Question Suggestions

4.8.16 New API (version

The suggested questions feature requires both appId and chatId. It automatically fetches the last 6 message turns from the session as context.

bash

curl --location --request POST 'http://localhost:3000/api/core/ai/agent/v2/createQuestionGuide' \
--header 'Authorization: Bearer [apikey]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "appId": "appId",
    "chatId": "chatId",
    "questionGuide": {
        "open": true,
        "model": "GPT-4o-mini",
        "customPrompt": "你是一个智能助手，请根据用户的问题生成猜你想问。"
    }
}'

</Tab> <Tab value="Parameters" >

参数名	类型	必填	说明
appId	string	✅	应用 Id
chatId	string	✅	Session ID
questionGuide	object		自定义配置，不传的话，则会根据 appId，取最新发布版本的配置

type CreateQuestionGuideParams = OutLinkChatAuthProps & {
  appId: string;
  chatId: string;
  questionGuide?: {
    open: boolean;
    model?: string;
    customPrompt?: string;
  };
};

</Tab> <Tab value="Response Example" >

json

{
  "code": 200,
  "statusText": "",
  "message": "",
  "data": ["你对AI有什么看法？", "想了解AI的应用吗？", "你希望AI能做什么？"]
}

</Tab> </Tabs>

Chat API

How to Get AppId

Start a Conversation

Start Chat

Request

Response

Response

Continue Interactive Node

Request Plugin

Request

Response

Chat CRUD

Session Management

Get Session List

Update Session Title

Update Session Pin Status

Delete a Session

Clear App Sessions

Message Management

Get Session Basic Info

Get Message List

Get Message Run Details

Delete Message

Update Feedback (Like / Dislike)

Question Suggestions