Rerank

Rerank a list of documents by relevance to a query.

Create Rerank

POST https://api.3xcoder.com/v1/rerank

Reranks documents based on their relevance to a given query, returning them in order of relevance with scores.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Reranking model ID
query	string	Yes	The query to compare documents against
documents	array	Yes	Array of document strings to rerank
top_n	integer	No	Number of top results to return. Default: all documents

Response

{
  "object": "list",
  "data": [
    {
      "object": "rerank.result",
      "index": 2,
      "relevance_score": 0.95
    },
    {
      "object": "rerank.result",
      "index": 0,
      "relevance_score": 0.72
    },
    {
      "object": "rerank.result",
      "index": 1,
      "relevance_score": 0.31
    }
  ],
  "model": "rerank-model",
  "usage": {
    "total_tokens": 150
  }
}

Examples

cURL

curl https://api.3xcoder.com/v1/rerank \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "rerank-model",
    "query": "What is machine learning?",
    "documents": [
      "Machine learning is a subset of artificial intelligence that enables systems to learn from data.",
      "The weather forecast predicts rain tomorrow.",
      "Deep learning uses neural networks with many layers to analyze complex patterns."
    ],
    "top_n": 2
  }'

Python

import requests

response = requests.post(
    "https://api.3xcoder.com/v1/rerank",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer your-api-key"
    },
    json={
        "model": "rerank-model",
        "query": "What is machine learning?",
        "documents": [
            "Machine learning is a subset of artificial intelligence that enables systems to learn from data.",
            "The weather forecast predicts rain tomorrow.",
            "Deep learning uses neural networks with many layers to analyze complex patterns."
        ],
        "top_n": 2
    }
)

results = response.json()
for item in results["data"]:
    print(f"Document {item['index']}: score {item['relevance_score']:.4f}")

JavaScript

const response = await fetch('https://api.3xcoder.com/v1/rerank', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
  },
  body: JSON.stringify({
    model: 'rerank-model',
    query: 'What is machine learning?',
    documents: [
      'Machine learning is a subset of artificial intelligence that enables systems to learn from data.',
      'The weather forecast predicts rain tomorrow.',
      'Deep learning uses neural networks with many layers to analyze complex patterns.'
    ],
    top_n: 2
  })
})

const data = await response.json()
data.data.forEach(item => {
  console.log(`Document ${item.index}: score ${item.relevance_score}`)
})