BGE Reranker v2 M3

curl https://llm.fixcloud.ai/v1/rerank \
  -H "Authorization: Bearer $FXC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-reranker-v2-m3",
    "query": "Which GPU is best for LLM inference?",
    "documents": [
      "The H200 has 141 GB of HBM3e memory.",
      "Istanbul is the largest city in Türkiye.",
      "Tensor parallelism splits a model across GPUs."
    ],
    "top_n": 2
  }'

import os, requests

response = requests.post(
    "https://llm.fixcloud.ai/v1/rerank",
    headers={"Authorization": f"Bearer {os.environ['FXC_API_KEY']}"},
    json={
        "model": "bge-reranker-v2-m3",
        "query": "Which GPU is best for LLM inference?",
        "documents": [
            "The H200 has 141 GB of HBM3e memory.",
            "Istanbul is the largest city in Türkiye.",
            "Tensor parallelism splits a model across GPUs.",
        ],
        "top_n": 2,
    },
)
for r in response.json()["results"]:
    print(r["index"], round(r["relevance_score"], 3))

const response = await fetch('https://llm.fixcloud.ai/v1/rerank', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FXC_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'bge-reranker-v2-m3',
    query: 'Which GPU is best for LLM inference?',
    documents: [
      'The H200 has 141 GB of HBM3e memory.',
      'Istanbul is the largest city in Türkiye.',
      'Tensor parallelism splits a model across GPUs.',
    ],
    top_n: 2,
  }),
});
const { results } = await response.json();
console.log(results);