Artificial Intelligence Recommendation:Call the recommendation engine API

API description

POST /api/rec/feed

Request parameters

item_list

If you have a batch of retrieved data to pass through the API, assign it to `item_list`. The `item_list` parameter is an array where each element is a map object. Each element must contain an `item_id` field, which specifies the item ID. All other fields are optional. If an element includes a `score` field, its value is treated as the retrieval score. Other fields are treated as item properties.

complex_type_features

Context features of complex types must be passed as an array. Each element contains the following fields:

Examples:

1. Pass a single value: [{"name":"age", "type":"int", "values":20}, {"name":"sex", "values":"male", "type":"string"}]

2. Pass an array: [{"name":"list_features", "type":"list<int>", "values":[1,2,3]}]

3. Pass a map: [{"name":"map_features", "type":"map<int,int>", "values":{"1":10,"2":20,"3":30}}], or [{"name":"map_features", "type":"map<int,int>", "values":{"1":"10","2":"20","3":"30"}}],

The `type` field supports the following types: int, int64, float, double, string, list<int>, list<int64>, list<float>, list<double>, list<string>, map<int,int>, map<int,int64>, map<int,float>, map<int,double>, map<int,string>, map<string,int>, map<string,int64>, map<string,float>, map<string,double>, map<string,string>, map<int64,int>, map<int64,int64>, map<int64,float>, map<int64,double>, and map<int64,string>.

Note: You can use `complex_type_features` and `features` at the same time when you pass context data.

Response

The following table describes the fields for each element in the `items` list.

Error codes

Configuration and call example

The following example shows how to use context retrieval. In this method, you pass a list of items to the API. The following configuration uses the `home_feed` scenario as an example:

{
  "RunMode": "product",
  "ListenConf": {
    "HttpAddr": "",
    "HttpPort": 8000
  },
  "SortNames": {
    "default": ["ItemRankScore"]
  },
  "FilterNames": {
    "default": ["UniqueFilter"]
  },
  "SceneConfs": {
    "home_feed": {
      "default": {
        "RecallNames": ["ContextItemRecall"]
      }
    }
  }
}

The request body is as follows:

{
  "uid":"13579",
  "size":10,
  "scene_id":"home_feed",
  "item_list":[{"item_id":"1111", "score":1},{"item_id":"222", "score":0.95}]
}

Call the API

Call the API using a curl command

To use a curl command to request the engine service from your local machine, first obtain the request URL and token for the service from the PAI-EAS console, as shown in the following figure:

On the service details page, click View Invocation Method to view the call information.

curl -X 'POST' -v \
'http://12*****.vpc.hangzhou.pai-eas.aliyuncs.com/api/predict/test/api/rec/feed' \
-H 'Authorization:YmRjZThkM2Z*****************TU5Mw==' \
-d '{
"uid":"13579",
"size":10,
"scene_id":"home_feed",
"item_list":[{"item_id":"1111", "score":1},{"item_id":"222", "score":0.95}]
}'

Response data

{
  "code":200,
  "msg":"success",
  "request_id":"e332fe9c-7d99-45a8-a047-bc7ec33d07f6",
  "size":10,
  "experiment_id":"",
  "items":[
    {
      "item_id":"1111",
      "score":0.9991594902203332,
      "retrieve_id":"ContextItemRecall"
    }
  ]
}

Call the API using the PAI-Rec diagnostic tool

If you deployed the service from the Service Management page in the PAI-Rec console, you can use the diagnostic tool to debug the recommendation results, as shown in the following figure:

Select the corresponding service and environment, and set the routing information to /api/rec/feed.

Item Table: If you have an item details table, you can select it here. The item details will be associated with the returned data.

Request Data: This section displays the request parameters from recent requests. You can also enter them manually.

As shown in the following figure, select and enter the relevant parameters, and then click Diagnose to obtain the recommendation results.