similarity-search-api-sdk

{'type': 'object', 'title': 'estimate_corpus_entropy_profileArguments', 'required': ['corpus_vectors'], 'properties': {'n_bins': {'type': 'number', 'title': 'N Bins', 'default': 16, 'maximum': 50, 'minimum': 3, 'description': 'Number of histogram bins for entropy discretization. Must be between 3 and 50; should match the n_bins used in rank_items_by_nmi_cosine_fusion for the profile to be consistent.'}, 'corpus_vectors': {'type': 'array', 'items': {'type': 'array', 'items': {'type': 'number'}}, 'title': 'Corpus Vectors', 'maxItems': 500000, 'minItems': 1, 'description': 'List of dense numeric vectors for which to compute the aggregate entropy and calibrated alpha. Each inner array must be the same length. Maximum 500000 entries.'}}}

{'type': 'object', 'title': 'rank_items_by_nmi_cosine_fusionArguments', 'required': ['query_vector', 'corpus_vectors'], 'properties': {'top_k': {'type': 'number', 'title': 'Top K', 'default': 10, 'maximum': 1000, 'minimum': 1, 'description': 'Number of top-ranked results to return, ordered by descending fusion score. Capped at 1000 by the core service regardless of corpus size.'}, 'n_bins': {'type': 'number', 'title': 'N Bins', 'default': 16, 'maximum': 50, 'minimum': 3, 'description': 'Number of histogram bins used to discretize continuous dimensions when estimating NMI. Must be between 3 and 50.'}, 'query_vector': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Query Vector', 'maxItems': 4096, 'minItems': 2, 'description': 'Dense numeric vector representing the query item. Must have the same dimensionality as all corpus_vectors entries.'}, 'alpha_override': {'type': 'number', 'title': 'Alpha Override', 'default': None, 'maximum': 1.0, 'minimum': 0.0, 'description': 'Fixed alpha weight for cosine component in [0.0, 1.0]. If omitted, alpha is auto-calibrated from corpus entropy. Set to 1.0 to use pure cosine; 0.0 for pure NMI.'}, 'corpus_vectors': {'type': 'array', 'items': {'type': 'array', 'items': {'type': 'number'}}, 'title': 'Corpus Vectors', 'maxItems': 500000, 'minItems': 1, 'description': 'List of dense numeric vectors forming the corpus to rank against. Each inner array must match query_vector dimensionality. Maximum 500000 entries.'}}}

{'type': 'object', 'title': 'score_pair_nmi_cosineArguments', 'required': ['vector_a', 'vector_b'], 'properties': {'alpha': {'type': 'number', 'title': 'Alpha', 'default': 0.5, 'maximum': 1.0, 'minimum': 0.0, 'description': 'Fixed alpha weight for the cosine component in [0.0, 1.0], applied as-is -- not auto-calibrated. Default 0.5 matches the core service default.'}, 'n_bins': {'type': 'number', 'title': 'N Bins', 'default': 16, 'maximum': 50, 'minimum': 3, 'description': 'Histogram bins for NMI discretization. Must be between 3 and 50.'}, 'vector_a': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Vector A', 'maxItems': 4096, 'minItems': 2, 'description': 'First dense numeric vector of the pair. Must have the same dimensionality as vector_b.'}, 'vector_b': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Vector B', 'maxItems': 4096, 'minItems': 2, 'description': 'Second dense numeric vector of the pair. Must have the same dimensionality as vector_a.'}}}