Retrieve agent history

Retrieve agent history

GET

https://api.agora.io/api/conversational-ai-agent/v2/projects/{appid}/agents/{agentId}/history

Call this endpoint while the agent is running to retrieve the conversation history between the user and the Conversational AI agent.

You can set the maximum number of cached entries using the llm.max_history parameter when calling Start a conversational AI agent. The default value is 32.

appid stringrequired

The App ID of the project.

agentId stringrequired

The agent instance ID you obtained after successfully calling join to Start a conversational AI agent.

• If the returned status code is 200, the request was successful. The response body contains the result of the request.

  OK

  • agent_id string

    Unique identifier of the agent.

  • start_ts integer

    Agent creation timestamp.

  • status string

    Possible values: RUNNING

    Agent status. Only supports querying the running agent.

  • contents array

    Agent history.

    • role string

      Possible values: user, assistant

      The message sender.

      • user: User
      • assistant: AI agent

    • content string

      Message content.

• If the returned status code is not 200, the request failed. The response body includes the error code and description. Refer to status codes to understand the possible reasons for failure.

Authorization

This endpoint requires Basic Auth.

Request example

• curl
• Python
• Node.js

_3

curl --request get \

_3

--url https://api.agora.io/api/conversational-ai-agent/v2/projects/:appid/agents/:agentId/history \

_3

--header 'Authorization: Basic <credentials>'

Response example

_15

{

_15

"agent_id": "xxxx",

_15

"start_ts": 123,

_15

"status": "RUNNING",

_15

"contents": [

_15

{

_15

"role": "user",

_15

"content": "hello."

_15

},

_15

{

_15

"role": "assistant",

_15

"content": "hi, how can I help you?"

_15

}

_15

]

_15

}