You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

804 B

Raw Blame History

Vector-sync HTTP embedding provider

This patch adds a new provider type:

http-vector-sync

Request

Endpoint:

POST {baseUrl}/vector-sync

Request body:

{
  "model": "intfloat/multilingual-e5-large",
  "text": "This is a sample text to vectorize"
}

Response

{
  "runtime_ms": 472.49,
  "vector": [0.1, 0.2, 0.3],
  "incomplete": false,
  "combined_vector": null,
  "token_count": 9,
  "model": "intfloat/multilingual-e5-large",
  "max_seq_length": 512
}

Notes

supports a single text per request
works for both document and query embeddings
validates returned vector dimension against the configured embedding model
keeps the existing /embed provider in place as http-json

Example config

See application-new-example-vector-sync-provider.yml.