Qdrant · Schema

RecommendStrategy

How to use positive and negative examples to find the results, default is `average_vector`: * `average_vector` - Average positive and negative vectors and create a single query with the formula `query = avg_pos + avg_pos - avg_neg`. Then performs normal search. * `best_score` - Uses custom search objective. Each candidate is compared against all examples, its score is then chosen from the `max(max_pos_score, max_neg_score)`. If the `max_neg_score` is chosen then it is squared and negated, otherwise it is just the `max_pos_score`. * `sum_scores` - Uses custom search objective. Compares against all inputs, sums all the scores. Scores against positive vectors are added, against negatives are subtracted.

AIArtificial IntelligenceVector Databases

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/RecommendStrategy",
  "title": "RecommendStrategy",
  "description": "How to use positive and negative examples to find the results, default is `average_vector`:\n\n* `average_vector` - Average positive and negative vectors and create a single query with the formula `query = avg_pos + avg_pos - avg_neg`. Then performs normal search.\n\n* `best_score` - Uses custom search objective. Each candidate is compared against all examples, its score is then chosen from the `max(max_pos_score, max_neg_score)`. If the `max_neg_score` is chosen then it is squared and negated, otherwise it is just the `max_pos_score`.\n\n* `sum_scores` - Uses custom search objective. Compares against all inputs, sums all the scores. Scores against positive vectors are added, against negatives are subtracted.",
  "type": "string",
  "enum": [
    "average_vector",
    "best_score",
    "sum_scores"
  ]
}