문서 · 연동

임베딩

POST /v1/embeddings turns text into vectors for semantic search, RAG, clustering and deduplication. Pick a model of type "Embedding".

본문은 현재 영어로만 제공됩니다.

curl https://<your-endpoint>/v1/embeddings \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["The quick brown fox", "jumps over the lazy dog"]
  }'

input can be a string or an array of strings; batching cuts the number of requests.
Vectors in one index must come from the same model. Changing models means re-embedding everything.
Split text that exceeds the model's input limit.

이미지 생성

모델 목록과 선택