ドキュメント · 導入
埋め込み
POST /v1/embeddings turns text into vectors for semantic search, RAG, clustering and deduplication. Pick a model of type "Embedding".
本文は現在英語版のみ提供しています。
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"]
}'inputcan 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.