Conversational AI Error Callback
Tencent RTC Conversational AI provides an error callback feature. These status callbacks are sent through Tencent RTC's custom messages, allowing easy monitoring of dialogue performance on the client side. For example, when LLM or TTS calls fail, the data is pushed to the terminal in real-time via Tencent RTC custom messages, enabling monitoring of Conversational AI quality and success rate.
Through the Tencent RTC SDK Receive Custom Messages feature, listen for callbacks on the client to receive data from the Conversational AI error callback. The cmdID is fixed at 1.
Field | Type | Description |
type | Number | Message type, 10030 indicates an AI service error callback |
sender | String | Sender's `userid`, which is the bot's ID |
payload | Object | Message payload, including details |
The payload object contains the following fields:
Field | Type | Description |
metric | String | The metric names are as follows asr_error llm_error tts_error |
tag | Object | Tag associated with the metric |
The tag object contains the following fields:
Field | Type | Description |
roundid | String | Dialogue round ID |
code | Number | Call Error Codes |
message | String | Detailed description of the error information |
Metric Name Description:
Status Code | Description |
asr_error | ASR recognition error |
llm_error | LLM request error |
tts_error | TTS request error |
Error Code List
Service Category | Error Code | Error Description |
ASR | 30100 | Request timeout |
| 30102 | Internal Error |
LLM | 30200 | LLM request timeout |
| 30201 | LLM request frequency limited |
| 30202 | LLM service returned failure |
TTS | 30300 | TTS service request timeout |
| 30301 | TTS request frequency limited |
| 30302 | TTS service returned failure |
Note:
Detailed error codes, such as third-party LLM and TTS error codes, will be wrapped in
tag.message
for quick issue identification and user notification.