unsw-luopan commented on issue #12879: URL: https://github.com/apache/apisix/issues/12879#issuecomment-3727755106
Hi @Baoyuantop , thanks for your reply. I add "http_statuses" in my
ai-proxy-multi health check config, but apisix still route my request to dead
llm service.
My config:
{
"id": "ai-proxy-multi-route",
"uri": "/llm/qwen-test",
"methods": [
"POST"
],
"plugins": {
"ai-proxy-multi": {
"instances": [
{
"name": "qwen32b-test",
"provider": "openai-compatible",
"weight": 8,
"auth": {
"header": {
"Authorization": "Bearer aaa"
}
},
"options": {
"model": "qwen3-32b-int4-local"
},
"override": {
"endpoint":
"http://10.150.9.179:9998/v1/chat/completions";
},
"checks": {
"active": {
"type": "[http](https://www.json.cn/http)",
"host": "10.150.9.179",
"port": 9998,
"https_verify_certificate": false,
"http_path": "/v1/models/qwen3-32b-int4-local",
"healthy": {
"interval": 1,
"successes": 1,
"http_statuses": [
200
]
},
"unhealthy": {
"interval": 1,
"http_failures": 1,
"http_statuses": [
400
]
}
}
}
},
{
"name": "qwen8b-test",
"provider": "openai-compatible",
"weight": 2,
"auth": {
"header": {
"Authorization": "Bearer aaa"
}
},
"options": {
"model": "qwen3-8b"
},
"override": {
"endpoint":
"http://172.16.3.30:9997/v1/chat/completions";
},
"checks": {
"active": {
"type": "[http](https://www.json.cn/http)",
"host": "172.16.3.30",
"port": 9997,
"https_verify_certificate": false,
"http_path": "/v1/models/qwen3-8b",
"healthy": {
"interval": 1,
"successes": 1,
"http_statuses": [
200
]
},
"unhealthy": {
"interval": 1,
"http_failures": 1,
"http_statuses": [
400
]
}
}
}
}
]
}
}
}
Reproduce: create ai-proxy-multi route to two llms, and test this lb route.
Then kill one llm service, and test this route. Apisix
health checking not works.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
