1

参考： https ://github.com/SeldonIO/seldon-core/blob/master/examples/models/sklearn_iris/sklearn_iris.ipynb https://github.com/SeldonIO/seldon-core/tree/master/examples/models /sklearn_spacy_text

#步骤完成

1. kubectl port-forward $(kubectl get pods -l istio=ingressgateway -n istio-system -o jsonpath='{.items[0].metadata.name}') -n istio-system 8003:80
2.kubectl create namespace john
3.kubectl config set-context $(kubectl config current-context) --namespace=john
4.kubectl create -f sklearn_iris_deployment.yaml

cat sklearn_iris_deployment.yaml
apiVersion: machinelearning.seldon.io/v1alpha2
kind: SeldonDeployment
metadata:
  name: seldon-deployment-example
  namespace: john
spec:
  name: sklearn-iris-deployment
  predictors:
  - componentSpecs:
    - spec:
        containers:
        - image: seldonio/sklearn-iris:0.1
          imagePullPolicy: IfNotPresent
          name: sklearn-iris-classifier
    graph:
      children: []
      endpoint:
        type: REST
      name: sklearn-iris-classifier
      type: MODEL
    name: sklearn-iris-predictor
    replicas: 1

kubectl get sdep -n john seldon-deployment-example -o json | jq .状态

  "deploymentStatus": {
    "sklearn-iris-deployment-sklearn-iris-predictor-0e43a2c": {
      "availableReplicas": 1,
      "replicas": 1
    }
  },
  "serviceStatus": {
    "seldon-635d389a05411932517447289ce51cde": {
      "httpEndpoint": "seldon-635d389a05411932517447289ce51cde.john:9000",
      "svcName": "seldon-635d389a05411932517447289ce51cde"
    },
    "seldon-bb8b177b8ec556810898594b27b5ec16": {
      "grpcEndpoint": "seldon-bb8b177b8ec556810898594b27b5ec16.john:5001",
      "httpEndpoint": "seldon-bb8b177b8ec556810898594b27b5ec16.john:8000",
      "svcName": "seldon-bb8b177b8ec556810898594b27b5ec16"
    }
  },
  "state": "Available"
}

5.这里我使用 istio 并按照这个文档https://docs.seldon.io/projects/seldon-core/en/v1.1.0/workflow/serving.html我做了同样的事情

Istio
Istio REST
Assuming the istio gateway is at <istioGateway> and with a Seldon deployment name <deploymentName> in namespace <namespace>:

A REST endpoint will be exposed at : http://<istioGateway>/seldon/<namespace>/<deploymentName>/api/v1.0/predictions

curl -s http://localhost:8003/seldon/john/sklearn-iris-deployment-sklearn-iris-predictor-0e43a2c/api/v0.1/predictions -H "Content-Type: application/json" -d ' {“数据”：{“ndarray”：[[5.964,4.006,2.081,1.031]]}}' -v

*   Trying 127.0.0.1...
* TCP_NODELAY set
* Connected to localhost (127.0.0.1) port 8003 (#0)
> POST /seldon/johnson-az-videspan/sklearn-iris-deployment-sklearn-iris-predictor-0e43a2c/api/v0.1/predictions HTTP/1.1
> Host: localhost:8003
> User-Agent: curl/7.58.0
> Accept: */*
> Content-Type: application/json
> Content-Length: 48
> 
* upload completely sent off: 48 out of 48 bytes
< HTTP/1.1 301 Moved Permanently
< location: https://localhost:8003/seldon/john/sklearn-iris-deployment-sklearn-iris-predictor-0e43a2c/api/v0.1/predictions
< date: Fri, 23 Oct 2020 13:09:46 GMT
< server: istio-envoy
< connection: close
< content-length: 0
< 
* Closing connection 0

同样的事情也发生在sklearn_spacy_text模型中，但我想知道相同的模型在 docker 上运行时能完美地工作。

请从 docker 找到示例响应

curl  -s http://localhost:5000/predict -H "Content-Type: application/json" -d '{"data":{"ndarray":[[5.964,4.006,2.081,1.031]]}}' -v
*   Trying 127.0.0.1...
* TCP_NODELAY set
* Connected to localhost (127.0.0.1) port 5000 (#0)
> POST /predict HTTP/1.1
> Host: localhost:5000
> User-Agent: curl/7.61.1
> Accept: */*
> Content-Type: application/json
> Content-Length: 48
> 
* upload completely sent off: 48 out of 48 bytes
* HTTP 1.0, assume close after body
< HTTP/1.0 200 OK
< Content-Type: application/json
< Content-Length: 125
< Access-Control-Allow-Origin: *
< Server: Werkzeug/1.0.0 Python/3.7.4
< Date: Fri, 23 Oct 2020 11:18:31 GMT
< 
{"data":{"names":["t:0","t:1","t:2"],"ndarray":[[0.9548873249364169,0.04505474761561406,5.7927447968952436e-05]]},"meta":{}}
* Closing connection 0

curl  -s http://localhost:5001/predict -H "Content-Type: application/json" -d '{"data": {"names": ["text"], "ndarray": ["Hello world this is a test"]}}'
{"data":{"names":["t:0","t:1"],"ndarray":[[0.6811839197596743,0.3188160802403257]]},"meta":{}}

任何人都可以帮助解决这个问题

4

1 回答 1

1

问题

您发出的请求似乎错误地尝试重定向到 https 协议（端口 443）

解决方案

使用https 而不是 http

curl -s https://localhost:8003/seldon/john/sklearn-iris-deployment-sklearn-iris-predictor-0e43a2c/api/v0.1/predictions -H "Content-Type: application/json" -d '{"data":{"ndarray":[[5.964,4.006,2.081,1.031]]}}' -v

将curl 与 -L 标志一起使用，指示 curl 遵循重定向。在这种情况下，服务器为 HTTP 请求返回了重定向响应（301 Moved Permanently）到http://localhost:8003. 重定向响应指示客户端发送一个额外的请求，这次使用 HTTPS，到https://localhost:8003.

更多关于它的信息。

于 2020-10-28T10:01:51.850 回答