Langsung ke konten utama
POST
/
v1
/
rerank
curl -X POST "https://api.lemondata.cc/v1/rerank" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "BAAI/bge-reranker-v2-m3",
    "query": "What is machine learning?",
    "documents": [
      "Machine learning is a subset of AI",
      "The weather is nice today",
      "Deep learning uses neural networks"
    ],
    "top_n": 2,
    "return_documents": true
  }'

{
  "results": [
    {
      "index": 0,
      "relevance_score": 0.95,
      "document": "Machine learning is a subset of AI"
    },
    {
      "index": 2,
      "relevance_score": 0.82,
      "document": "Deep learning uses neural networks"
    }
  ],
  "model": "BAAI/bge-reranker-v2-m3",
  "usage": {
    "prompt_tokens": 45,
    "total_tokens": 45
  }
}
Urutkan ulang dokumen menggunakan model kesamaan semantik. Berguna untuk meningkatkan hasil pencarian dan aplikasi RAG.

​
Request Body

​
model
string
wajib
ID model reranker yang akan digunakan (misalnya, BAAI/bge-reranker-v2-m3, qwen3-rerank).
​
query
string
wajib
Kueri untuk membandingkan peringkat dokumen.
​
documents
array
wajib
Daftar dokumen (string) untuk diurutkan ulang.
​
top_n
integer
Jumlah hasil teratas yang akan dikembalikan. Default ke semua dokumen.
​
return_documents
boolean
default:"false"
Apakah akan menyertakan teks dokumen asli dalam respons.

​
Respons

​
results
array
Daftar dokumen yang telah diurutkan beserta skornya.Setiap hasil berisi:
  • index (integer): Indeks dokumen asli
  • relevance_score (number): Skor relevansi (0-1)
  • document (string): Teks asli (jika return_documents=true)
​
model
string
Model yang digunakan untuk reranking.
​
usage
object
Statistik penggunaan token.
curl -X POST "https://api.lemondata.cc/v1/rerank" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "BAAI/bge-reranker-v2-m3",
    "query": "What is machine learning?",
    "documents": [
      "Machine learning is a subset of AI",
      "The weather is nice today",
      "Deep learning uses neural networks"
    ],
    "top_n": 2,
    "return_documents": true
  }'

{
  "results": [
    {
      "index": 0,
      "relevance_score": 0.95,
      "document": "Machine learning is a subset of AI"
    },
    {
      "index": 2,
      "relevance_score": 0.82,
      "document": "Deep learning uses neural networks"
    }
  ],
  "model": "BAAI/bge-reranker-v2-m3",
  "usage": {
    "prompt_tokens": 45,
    "total_tokens": 45
  }
}