World-Class Medical Reranker
Maximize search relevancy and RAG accuracy for healthcare queries. Outperforms Jina, Cohere, and Vertex AI on medical benchmarks.
Trained on 102 healthcare sources + 10M PubMed papers:
Your app retrieves 100 documents using embeddings or BM25
Persly Rerank analyzes query-document pairs jointly (not independently like embeddings)
Returns top_k most relevant documents with scores 0-1
Unlike embeddings (encode separately), cross-attention encodes query + document together, capturing fine-grained semantic relationships. This is crucial for medical queries with complex terminology.
curl https://api.persly.ai/v1/rerank \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "What are the side effects of metformin for diabetes?",
"documents": [
"Metformin is a first-line medication for type 2 diabetes...",
"Common side effects include nausea, diarrhea, and stomach upset...",
"SGLT2 inhibitors are an alternative class of diabetes medications..."
],
"top_k": 6
}'| Model | NDCG@10 | Recall@10 | Latency (p95) |
|---|---|---|---|
| Persly Rerank | 0.68 | 91% | 185ms |
| Cohere Rerank 4 | 0.63 | 86% | 195ms |
| Jina Reranker v3 | 0.61 | 84% | 210ms |
| Vertex AI Ranking | 0.59 | 79% | 240ms |
* Benchmarks from internal testing on healthcare QA datasets. Contact us for detailed methodology and datasets.
Boost RAG accuracy by 40%+ with precise document selection
Rerank BM25/embedding results for maximum relevancy
Find the exact paragraph that answers medical questions
Classify medical documents by relevance to specific topics
Use Rerank after embeddings when precision matters more than speed. It improves NDCG@10 by ~15% but adds ~50ms latency.
Up to 1,000 documents per request. For best performance, rerank top 100-200 from your initial search.
Yes. Supports 100+ languages with cross-lingual matching (e.g., Korean query → English docs).
Scores range from 0 to 1, representing the probability that a document is relevant to the query. Higher is better.
Let's discuss how our APIs can power your healthcare product