curl -s http://localhost:8000/v1/embeddings -H 'Content-Type: application/json' -d '{"model":"BAAI/bge-small-en-v1.5","input":"Hello world"}'

Category: AI/ML Tooling

curl -s http://localhost:8000/v1/embeddings -H 'Content-Type: application/json' -d '{"model":"BAAI/bge-small-en-v1.5","input":"Hello world"}'

Generate text embeddings via vLLM

Sends text to the embeddings endpoint and receives a vector per input, ready for semantic search or clustering. The served model must be an embedding model like bge-small-en-v1.5, not a chat model. Response vectors appear under data[0].embedding, often truncated by the terminal, so pipe to a file.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.