Skip to main content
POST
/
v1
/
rerank
curl https://qingbo.dev/v1/rerank \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina-reranker-v2-base-multilingual",
    "query": "什么是机器学习？",
    "documents": [
      "机器学习是人工智能的一个分支",
      "今天天气很好",
      "深度学习使用神经网络进行特征学习"
    ]
  }'
Synchronous endpoint — reranks candidate documents by their relevance to a query text. Commonly used for RAG (Retrieval-Augmented Generation). Parameters are passed through directly to the upstream model. 
curl https://qingbo.dev/v1/rerank \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina-reranker-v2-base-multilingual",
    "query": "什么是机器学习？",
    "documents": [
      "机器学习是人工智能的一个分支",
      "今天天气很好",
      "深度学习使用神经网络进行特征学习"
    ]
  }'

​
Request Parameters

​
model
string
required
Reranking model ID, e.g., jina-reranker-v2-base-multilingual
​
query
string
required
Query text
​
documents
string[]
required
Candidate documents array
​
top_n
integer
Return the top N most relevant documents