重排序#

學習如何在 XInference 中使用重新排序模型。

introduction#

給定一個查詢和一系列文檔，Rerank 會根據與查詢的語義相關性從最相關到最不相關對文檔進行重新排序。在 Xinference 中，可以透過 Rerank 端點呼叫 Rerank 模型來對一系列文檔進行排序。

快速入門#

我們可以透過cURL、OpenAI Client或Xinference來嘗試使用Rerank API：

curl -X 'POST' \
  'http://<XINFERENCE_HOST>:<XINFERENCE_PORT>/v1/rerank' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "<MODEL_UID>",
    "query": "A man is eating pasta.",
    "documents": [
        "A man is eating food.",
        "A man is eating a piece of bread.",
        "The girl is carrying a baby.",
        "A man is riding a horse.",
        "A woman is playing violin."
    ]
  }'

from xinference.client import Client

client = Client("http://<XINFERENCE_HOST>:<XINFERENCE_PORT>")
model = client.get_model(<MODEL_UID>)

query = "A man is eating pasta."
corpus = [
    "A man is eating food.",
    "A man is eating a piece of bread.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
    "A woman is playing violin."
]
print(model.rerank(corpus, query))

{
    "id": "480dca92-8910-11ee-b76a-c2c8e4cad3f5",
    "results": [{
        "index": 0,
        "relevance_score": 0.9999247789382935,
        "document": "A man is eating food."
    }, {
        "index": 1,
        "relevance_score": 0.2564932405948639,
        "document": "A man is eating a piece of bread."
    }, {
        "index": 3,
        "relevance_score": 0.00003955026841140352,
        "document": "A man is riding a horse."
    }, {
        "index": 2,
        "relevance_score": 0.00003742107219295576,
        "document": "The girl is carrying a baby."
    }, {
        "index": 4,
        "relevance_score": 0.00003739788007806055,
        "document": "A woman is playing violin."
    }]
}