langchain_experimental.recommenders.amazon_personalize
.AmazonPersonalize¶
- class langchain_experimental.recommenders.amazon_personalize.AmazonPersonalize(campaign_arn: Optional[str] = None, recommender_arn: Optional[str] = None, client: Optional[Any] = None, credentials_profile_name: Optional[str] = None, region_name: Optional[str] = None)[source]¶
Amazon Personalize实时操作运行时包装器。
更多信息请参阅[此链接](https://docs.aws.amazon.com/personalize/latest/dg/API_Operations_Amazon_Personalize_Runtime.html).
- 参数
campaign_arn (可选[str]) – str,可选:用于获取推荐项活动的Amazon资源名称(ARN)。
recommender_arn (可选[str]) – str,可选:用于获取推荐项的推荐器 Amazon资源名称(ARN)
client (可选[Any]) – 可选:boto3客户端
credentials_profile_name (可选[str]) – str,可选:AWS配置文件名
region_name (可选[str]) – str,可选:AWS区域,例如 us-west-2
示例
- personalize_client = AmazonPersonalize (
campaignArn=’<my-campaign-arn>’ )
方法
__init__
([campaign_arn, recommender_arn, ...])get_personalized_ranking
(user_id, input_list)为给定用户重新排序推荐项列表。
get_recommendations
([user_id, item_id, ...])从Amazon Personalize服务中获取推荐。
- __init__(campaign_arn: Optional[str] = None, recommender_arn: Optional[str] = None, client: Optional[Any] = None, credentials_profile_name: Optional[str] = None, region_name: Optional[str] = None)[源代码]¶
- 参数
campaign_arn (可选[str]) –
recommender_arn (可选[str]) –
client (可选[Any]) –
credentials_profile_name (可选[str]) –
region_name (可选[str]) –
- get_personalized_ranking(user_id: str, input_list: List[str], filter_arn: Optional[str], filter_values: Optional[Mapping[str, str]], context: Optional[Mapping[str, str]], metadata_columns: Optional[Mapping[str, Sequence[str]]], **kwargs: Any) Mapping[str, Any] [来源]¶
为给定用户重新排序推荐项列表。
https://docs.aws.amazon.com/personalize/latest/dg/API_RS_GetPersonalizedRanking.html
- 参数
user_id (str) – 字符串,必需:检索推荐的用户标识符
input_list (List[str]) – List[str],必需:按itemId排列的项目列表
filter_arn (Optional[str]) – string,可选:应用此过滤器的ARN
filter_values (Optional[Mapping[str, str]]) – Mapping,可选:过滤推荐时使用的值。
context (Optional[Mapping[str, str]]) – Mapping,可选:获取推荐时使用的上下文元数据
metadata_columns (Optional[Mapping[str, Sequence[str]]]) – Mapping,可选:作为响应部分返回的元数据列。
kwargs (Any) –
- 返回值
- Mapping[str, Any]: 返回个性化排名
和推荐Id。
- 返回类型
response
示例
personalize_client = AmazonPersonalize(campaignArn='<my-campaign-arn>')
- response = personalize_client.get_personalized_ranking(user_id="1",
input_list=["123,"256"])
- get_recommendations(user_id: Optional[str] = None, item_id: Optional[str] = None, filter_arn: Optional[str] = None, filter_values: Optional[Mapping[str, str]] = None, num_results: Optional[int] = 10, context: Optional[Mapping[str, str]] = None, promotions: Optional[Sequence[Mapping[str, Any]]] = None, metadata_columns: Optional[Mapping[str, Sequence[str]]] = None, **kwargs: Any) Mapping[str, Any] [source]¶
从Amazon Personalize服务中获取推荐。
请参阅更多详情: https://docs.aws.amazon.com/personalize/latest/dg/API_RS_GetRecommendations.html
- 参数
user_id (可选[str]) – str, 可选:要检索推荐的用户标识符
item_id (可选[str]) – str, 可选:要检索推荐的项标识符
filter_arn (可选[str]) – str, 可选:应用于返回推荐的筛选器ARN
filter_values (Optional[Mapping[str, str]]) – Mapping,可选:过滤推荐时使用的值。
num_results (可选[int]) – int, 可选:默认=10:要返回的结果数量
context (Optional[Mapping[str, str]]) – Mapping,可选:获取推荐时使用的上下文元数据
promotions (可选[Sequence[Mapping[str, Any]]]) – Sequence, 可选:应用于推荐请求的推广。
metadata_columns (Optional[Mapping[str, Sequence[str]]]) – Mapping,可选:作为响应部分返回的元数据列。
kwargs (Any) –
- 返回值
Mapping[str, Any]: 返回itemList和recommendationId。
- 返回类型
response
示例
personalize_client = AmazonPersonalize(campaignArn='<my-campaign-arn>')
response = personalize_client.get_recommendations(user_id="1")