gRPC API

Overview

This page documents the ML gRPC ingestion API for classic model monitoring workflows. If you’re looking for the current Arize AX REST API for datasets, experiments, and broader platform automation, see Arize REST API. Arize’s APIs are the main ingresses for data which powers our platform. Most applications will use an existing SDK in the language of your choice, but it’s important to know what the underlying API looks like first in case you want to work in a language without a current SDK implementation.

Authentication

Arize uses API keys in conjunction with a Space id in order to authenticate request. You will receive your keys once you sign up for our product. Your API and Space id are the keys to your data castle so be sure to keep them secure. Do not share your keys in public forums including Github, StackOverflow, logs, etc. Both the API key and Space ID are is authenticated via auth headers, use -H 'Authorization: API_KEY_VALUE' -H 'Grpc-Metadata-arize-space-id: SPACE_ID' -H 'Grpc-Metadata-sdk-language: rest Arize uses conventional HTTP response codes to convey resulting success or failure of a given request. Codes in the 2XX range indicate success, 4XX range indicate content failure, 5XX indicate errors with Arize’s edge servers.

Status Code	Message	Reason
200	OK	Success
403	cannot access request headers	Failure when accessing incoming request’s headers
403	must provide authorization header	Missing Authorization header
403	unable to validate authorization header	Space id is not valid
403	invalid api-key	API Key is not valid
400	log must include prediction or actual	Prediction or Actual is a required field and it’s not present
400	invalid feature type	Feature data type is not supported
400	timestamp must range from now back to T-90 days	Record timestamp can only be backdated up to 90 days
500	Internal service error, contact Arize	Internal error processing messages - Contact Arize

Full Record

To send an individual prediction record, you should hit Arize’s log API https://api.arize.com/v1/log

Supported label types

Label	data type
”numeric”	double
”score categorical”	Tuple (string, float)

Request Example (numeric label)

curl --request POST 'https://api.arize.com/v1/log' \
--header 'Authorization: API_KEY' \
--header 'Grpc-Metadata-arize-space-id: SPACE_ID' \
--header 'Grpc-Metadata-sdk-language: rest' \
--data-raw '{
   "model_id":"example_model_id",
   "prediction_id":"ef00f52c-d6d4-4e48-84cd-70166b3f423f",
   "prediction":{
      "timestamp":"2020-10-02T00:37:30.208687Z",   //Optional, defaults to now()
      "model_version":"v0.1",
      "label":{
         "numeric":0.1
      },
      "features":{
         "feature_1_float":{
            "double":0.6604474844066184
         },
         "feature_2_str":{
            "string":"str val"
         },
         "feature_4_bool":{
            "string":"True"
         },
         "feature_2_float":{
            "double":0.02876647860632975
         },
         "feature_3_float":{
            "double":0.3358383777892534
         },
         "feature_0_np_ll":{
            "int":"77"
         },
         "feature_3_bool":{
            "string":"True"
         },
         "feature_1_str":{
            "string":"str val"
         },
         "feature_1_np_ll":{
            "int":"1"
         },
         "feature_4_float":{
            "double":0.9681327640084113
         },
         "image_embedding":{
            "embedding":{
               "vector":[
                  1.0,
                  2.0,
                  3.0
               ],
               "link_to_data":"https://my-bucket.s3.us-west-2.amazonaws.com/puppy.png"
            }
         },
         "feature_2_bool":{
            "string":"True"
         },
         "feature_2_np_ll":{
            "int":"91"
         },
         "feature_0_str":{
            "string":"str val"
         },
         "feature_4_np":{
            "double":0.543297819558724
         },
         "feature_1_bool":{
            "string":"True"
         },
         "feature_3_np":{
            "double":0.5149428483266209
         },
         "feature_4_str":{
            "string":"str val"
         },
         "nlp_embedding_sentence":{
            "embedding":{
               "vector":[
                  4.0,
                  5.0,
                  6.0,
                  7.0
               ],
               "link_to_data":"",
               "raw_data":{
                  "tokenArray":{
                     "tokens":[
                        "This is a test sentence"
                     ]
                  }
               }
            }
         },
         "feature_2_np":{
            "double":0.29966708188607294
         },
         "feature_3_np_ll":{
            "int":"46"
         },
         "feature_1_np":{
            "double":0.8751167134832335
         },
         "feature_0_np":{
            "double":0.3854629460534247
         },
         "feature_0_bool":{
            "string":"True"
         },
         "feature_4_np_ll":{
            "int":"74"
         },
         "feature_0_float":{
            "double":0.5696514798125208
         },
         "feature_3_str":{
            "string":"str val"
         },
         "nlp_embedding_tokens":{
            "embedding":{
               "vector":[
                  4.0,
                  5.0,
                  6.0,
                  7.0
               ],
               "link_to_data":"",
               "raw_data":{
                  "tokenArray":{
                     "tokens":[
                        "This",
                        "is",
                        "a",
                        "test",
                        "token",
                        "array"
                     ]
                  }
               }
            }
         }
      },
      "tags":{
         "tag_str":{
            "string":"arize"
         },
         "tag_int":{
            "int":"0"
         },
         "tag_double":{
            "double":20.2
         },
         "tag_bool":{
            "string":"True"
         }
      }
   },
   "actual":{
      "label":{
         "numeric":0.1
      },
      "tags":{
         "tag_str":{
            "string":"arize"
         },
         "tag_int":{
            "int":"0"
         },
         "tag_double":{
            "double":20.2
         },
         "tag_bool":{
            "string":"True"
         }
      }
   },
   "environment_params":{
      "production":{
         
      }
   }
}'

Actual

To send an individual actual record, you should hit Arize’s log API https://api.arize.com/v1/log

Supported label types

Label	data type
”numeric”	double
”score categorical”	Tuple (string, float)

Request Example (score categorical label)

curl --request POST 'https://api.arize.com/v1/log' \
--header 'Authorization: API_KEY' \
--header 'Grpc-Metadata-arize-space-id: SPACE_ID' \
--header 'Grpc-Metadata-sdk-language: rest' \
--data-raw '
{
   "model_id":"example_model_id",                          //Required
   "prediction_id":"027ed30c-6333-4eab-9492-61e117b1b46f", //Required
   "actual":{                                              //Required
      "label":{
         "score_categorical":{
            "score_category":{
               "category":"orange",
               "score":1.0
            }
         }
      }
   },
   "environment_params":{                                  //Required
      "production":{
         
      }
   }
}'

Questions? Email us at support@arize.com or Slack us in the #arize-support channel

Quickstart

Instrument

Observe

Evaluate

Improve

Agents

Machine Learning

Settings

Security

Overview

Authentication

Full Record

Supported label types

Request Example (numeric label)

Actual

Supported label types

Request Example (score categorical label)

​Overview

​Authentication

​Full Record

​Supported label types

​Request Example (numeric label)

​Actual

​Supported label types

​Request Example (score categorical label)

Overview

Authentication

Full Record

Supported label types

Request Example (numeric label)

Actual

Supported label types

Request Example (score categorical label)