jiqq opened a new issue, #13213:
URL: https://github.com/apache/apisix/issues/13213

   ### Description
   
   I have rerank  server,the request url  is 
`http://172.32.150.72:8008/v1/rerank` and` http://172.32.150.72:8008/score`,I 
want to use ai-multi-proxy plugin ,because the endpoint must compled like 
http://ip:port/path
   how to proxy both  `http://172.32.150.72:8008/v1/rerank`  and 
`http://172.32.150.72:8008/score`
   my route config is 
   ```
   {
       "modifiedIndex": 50332,
       "value": {
           "plugins": {
               "ai-proxy-multi": {
                   "instances": [
                       {
                           "provider": "openai-compatible",
                           "auth": {
                               "header": {
                                   "Authorization": "Bearer 
sk-21784d812fbc5d2ca3d3cbe02c9201b06cbad1372c237ecc"
                               }
                           },
                           "options": {
                               "model": "/models/Qwen3-Reranker-0.6B"
                           },
                           "weight": 100,
                           "name": "llm-instance-0",
                           "override": {
                               "endpoint": "http://172.32.150.72:8008";
                           }
                       }
                   ],
                   "fallback_strategy": [
                       "rate_limiting",
                       "http_429",
                       "http_5xx"
                   ]
               },
              
               "limit-conn": {
                   "key_type": "var",
                   "rejected_code": 503,
                   "rejected_msg": "Requests are too frequent, please try again 
later.",
                   "default_conn_delay": 0.1,
                   "conn": 11,
                   "burst": 0,
                   "key": "server_addr"
               },
               "proxy-rewrite": {
                   "regexUri": [
                       "^/.*",
                       "$0"
                   ],
                   "empty": false
               }
           },
           "create_time": 1775733072,
           "timeout": {
               "connect": 3,
               "read": 180,
               "send": 10
           },
           "id": "4850-1",
           "plugin_config_id": "2",
           "update_time": 1776081582,
           "enable_websocket": false,
           "methods": [
               "POST"
           ],
           "uri": "/*",
           "priority": 3
       },
       "key": "/apisix/routes/4850-1",
       "createdIndex": 50314
   }
   ```
   when request
   ```
   curl -X 'POST' \
     'http://172.32.150.72:8008/v1/rerank' \
     -H 'accept: application/json' \
     -H 'Content-Type: application/json' \
     -H "Authorization: Bearer 
sk-21784d812fbc5d2ca3d3cbe02c9201b06cbad1372c237ecc" \
     -d '{
     "model": "/models/Qwen3-Reranker-0.6B",
     "query": "What is the capital of France?",
     "documents": [
       "The capital of Brazil is Brasilia.",
       "The capital of France is Paris.",
       "Horses and cows are both animals"
     ],
     "top_n":2
   }'
   ```
   response  `{"detail":"Not Found"}`
   
   ### Environment
   
   - APISIX version (run `apisix version`):
   - Operating system (run `uname -a`):
   - OpenResty / Nginx version (run `openresty -V` or `nginx -V`):
   - etcd version, if relevant (run `curl 
http://127.0.0.1:9090/v1/server_info`):
   - APISIX Dashboard version, if relevant:
   - Plugin runner version, for issues related to plugin runners:
   - LuaRocks version, for installation issues (run `luarocks --version`):
   


-- 
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]

Reply via email to