Skip to main content

Rerank

Rerank models sort text passages / documents by semantic relevance to a specific query. They are often used to sort search results returned by an existing search solution.

Let's try to identify the 3 most relevant documents for a specific question:​

import requests

def rerank_openai(query, documents, api_base, model, api_key=None, top_n=None):
    url = f"{api_base}/v1/rerank"
    headers = {
        "Content-Type": "application/json"
    }
    if api_key:
        headers["Authorization"] = f"Bearer {api_key}"
    payload = {
        "model": model,
        "query": query,
        "documents": documents,
    }
    if top_n is not None:
        payload["top_n"] = top_n

    response = requests.post(url, headers=headers, json=payload)
    response.raise_for_status()
    return response.json()

The benefits of reranking are easier to understand when working with a large array of documents. We've prepared a special guide where we improve keyword search accuracy using CompressaRerank.