libs.teradata.langchain_teradata.TeradataVectorStore.similarity_search_by_vector = similarity_search_by_vector(self, **kwargs)

DESCRIPTION:
    Performs similarity search in the Vector Store for
    the input question vector or embedded question stored in the table.
    The algorithm specified in "search_algorithm" is used to perform
    the search against the vector store.
    The result contains "top_k" rows along with similarity score
    found by the "search_algorithm".
    Note:
        Applicable only for 'embeddings-based' Vector Store.
 
PARAMETERS:
    question:
        Optional Argument.
        Specifies the vector for a question,
        i.e., embeddings generated for a question.
        Types: str
 
    data:
        Optional Argument.
        Specifies table name or corresponding
        teradataml DataFrame where the question is stored.
        Note: Only one question(row) should be present
              in the table.
        Types: str or DataFrame
 
    column:
        Optional Argument.
        Specifies the column name which contains the
        question in embedded format.
        Types: str
 
    input_table:
        Optional Argument.
        A table that contains the question in embedded form.
        Types: str
 
    batch_vector_column:
        Optional for batch mode.
        The column that contains the questions in embedded form for batch mode.
        Note:
            Applicable only for AWS.
        Types: str
 
    top_k:
        Optional Argument.
        Specifies the number of similarity matches to be generated.
        Default Value: 10
        Permitted Values: [1 - 1024]
        Types: int
 
    search_threshold:
        Optional Argument.
        Threshold value to consider matching tables/views while searching.
        A higher threshold value limits responses to the top matches only.
        Note:
            Only applicable when "search_algorithm" is 'VECTOR_DISTANCE' AND 'KMEANS'.
        Types: float
 
    search_numcluster:
        Optional Argument.
        Number of clusters or fraction of train_numcluster to be considered while searching.
        Notes:
            Applicable when "search_algorithm" is 'KMEANS'.
            If you want to pass a fraction of train_numcluster to be used for searching,
            the supported range is (0, 1.0].
            If you want to pass the exact number of clusters to be used for searching,
            the supported range is [1, train_numcluster].
        Types: int or float
 
    ef_search:
        Optional Argument.
        Specify the number of neighbors to consider during search in HNSW graph.
        Note:
            Applicable when "search_algorithm" is 'HNSW'.
        Permitted Values: [1 - 1024]
        Types: int
 
    filter:
        Optional Argument.
        Specifies the filter expression to be used for filtering the results.
        Supports logical operators (AND, OR, NOT), comparison operators
        (=, !=, <, <=, >, >=), and IN clauses with parentheses grouping.
        Notes:
            Examples:
            * Simple condition: "age > 25"
            * Complex condition: "age >= 18 AND status = 'active'"
            * IN clause: "category IN ('A', 'B', 'C')"
            * Grouped conditions: "(age > 18 AND status = 'active') OR priority = 'high'"
            * String matching: "name != 'test' AND description LIKE '%important%'"
        Types: str
 
    filter_style:
        Optional Argument.
        Specifies whether to apply filtering before or after the similarity_search.
        Default Value: PRE-FILTERING
        Permitted Values: PRE-FILTERING, POST-FILTERING
        Types: str
 
    maximal_marginal_relevance:
        Optional Argument.
        Specifies whether to use Maximal Marginal Relevance (MMR) for retrieving documents.
        Types: bool
 
    lambda_multiplier:
        Optional Argument.
        Lambda multiplier to control the trade-off between relevance and diversity when selecting documents.
        Permitted Values: 0.0 to 1.0
        Types: float
 
    batch_data:
        Required for batch mode.
        Specifies the table name or teradataml DataFrame to be indexed for batch mode.
        Note:
            Applicable only for AWS.
        Types: str, teradataml DataFrame
 
    batch_id_column:
        Required for batch mode.
        Specifies the ID column to be indexed for batch mode.
        Note:
            Applicable only for AWS.
        Types: str
 
    return_type:
        Optional Argument.
        Specifies the return type of similarity_search.
        Default Value: teradataml
        Permitted Values: teradataml, pandas, json
        Types: str
 
RETURNS:
    list.
 
RAISES:
    TeradataMlException.
 
EXAMPLES:
    >>> from langchain_teradata import TeradataVectorStore
    >>> from teradatagenai import load_data
 
    # Create an instance of the embedding-based TeradataVectorStore.
    >>> load_data('amazon', 'amazon_reviews_embedded')
    >>> vs = TeradataVectorStore.from_embeddings(name = "vs",
                                                 data = 'amazon_reviews_embedded',
                                                 data_columns = ['embedding'])
 
    # Check the status of Vector Store creation.
    >>> vs.status()
 
    # Example 1: Perform similarity search in the Vector Store for
    #            the input question.
    >>> response = vs.similarity_search_by_vector(question='-0.06944,0.080352,0.045963,0.006985,-0.000496,-0.025461,0.045302,-0.028107,0.031248,0.00077,-0.028107,0.016781,-0.023147,-0.068779,-0.07936,-0.030091,0.027611,-0.047616,-0.025461,0.029595,0.024635,-0.025461,-0.029926,0.046294,-0.065142,-0.019013,0.037366,-0.008019,0.065472,-0.054891,-0.009507,0.022816,0.009341,-0.041995,0.022651,0.028603,0.059851,0.047286,0.014467,0.002118,0.016616,-0.009383,-0.001643,0.015624,0.002831,0.005539,0.0248,0.018517,-0.007109,-0.013723,0.029926,0.006903,-0.011325,0.075723,0.009259,0.043648,0.035382,-0.02943,0.023147,-0.036208,-0.017856,-0.032736,0.019013,-0.037035,0.022155,-0.036704,-0.003596,-0.012069,0.021824,0.013805,-0.062827,0.016616,0.008928,-0.04431,-0.019592,-0.002397,0.048608,-0.00341,-0.024139,0.006985,-0.005001,0.002542,0.001777,0.002025,0.026123,0.055883,0.015707,0.014963,0.024304,0.001157,0.042326,-0.004753,-0.044971,0.005373,0.074731,0.002728,-0.028934,0.032736,0.011573,-0.012483,-0.040507,0.040507,0.001736,-0.036539,0.028438,0.053568,0.048278,0.082006,0.011739,0.064811,0.034059,0.062496,-0.013309,-0.065803,0.05456,-0.046624,0.009837,0.005539,-0.015376,0.016947,-0.065472,0.015128,-0.018352,0.062496,0.005539,-0.036208,0.001715,-0.023643,-0.000646,-0.047616,0.035712,0.011325,0.013723,0.07936,-0.010375,-0.021989,0.030091,0.013475,0.038358,-0.034059,-0.068118,0.013475,0.036043,-0.017029,-0.028107,-0.002687,0.00992,-0.001963,-0.04431,-0.009052,-0.088619,-0.016699,-0.027611,0.006861,-0.046624,-0.047286,-0.00744,0.00187,0.004133,-0.008225,-0.018352,0.001405,-0.033067,-0.000858,-0.001705,-0.028107,-0.01984,-0.010251,-0.013888,0.002005,0.046294,0.025461,-0.021163,-0.044971,-0.034886,-0.010747,-0.024304,0.006035,-0.019344,0.001126,-0.018352,0.015045,0.02728,-0.020749,0.000527,0.007523,-0.019427,-0.010499,0.038027,-0.027445,-0.018931,0.021659,0.037035,-0.054891,0.005539,-0.051254,-0.003968,0.011739,-0.041003,0.017029,0.011408,-0.007564,0.051584,0.010499,-0.001788,0.001075,0.032902,0.020997,-0.015624,0.020749,0.038027,0.020749,-0.046955,-0.012069,0.050262,-0.048608,0.028934,-0.074731,0.025461,-0.056875,0.013971,-0.018104,-0.054891,-0.001343,0.013888,0.019427,0.038688,0.057536,-0.011077,0.082006,0.024139,0.033894,0.037366,0.02943,-0.026619,-0.032075,-0.040672,-0.021493,0.001891,-0.013805,-0.005415,0.016451,-0.001963,0.003617,0.003286,0.016533,-0.071424,-0.042987,0.023808,-0.071424,0.008101,0.018683,-0.037862,-0.036208,0.037366,0.006531,0.016203,0.031083,-0.006448,0.008349,-0.045963,0.012648,0.032571,-0.007688,-0.043318,0.025792,0.000889,0.015211,-0.018765,-0.013061,0.040176,-0.035712,0.02232,-0.011243,-0.030091,-0.04431,-0.059851,0.011904,-0.013888,0.060182,0.04431,-0.017691,-0.008721,-0.000509,-0.010375,-0.033563,-0.03968,-0.018104,0.010044,0.020005,-0.024304,0.046955,0.001447,0.017029,-0.011739,-0.042326,0.014219,0.036539,0.028768,-0.008597,-0.005745,0.00868,-0.040011,-0.036704,0.007192,-0.042326,0.061504,0.015789,-0.023147,-0.005373,-0.039184,0.014053,-0.000713,0.003038,-0.009135,0.012483,-0.028107,-0.014549,-0.060512,0.048939,-0.069771,0.000607,0.012648,0.017195,0.018683,0.008804,0.030918,-0.038027,-0.00279,0.027611,0.007068,0.031579,0.029099,-0.004898,0.04431,-0.056875,-0.034886,-0.008267,-0.005911,-0.018517,0.009837,0.0248,0.023147,0.04464,-0.017029,0.016285,-0.0124,0.030091,0.012069,-0.013392,-0.000163,0.038027,0.008721,0.005621,-0.015707,-0.062827,-0.060182,0.026453,0.028107,0.015293,0.014219,-0.047616,0.006076,0.032571,-0.047616,-0.027115,0.046294,-0.006985,-0.027445,0.005167,-0.03191,-0.009383,-0.022981,0.025957,0.001974,0.010127,-0.038854,-0.020253,-0.046955,0.011408,-0.047616,0.006985,-0.058198,0.021989,-0.001674,0.011987,-0.006861,0.043979,0.011408,-0.007853,-0.03439,0.025957,0.013557,0.02976,0.008721,-0.012731,-0.054891,-0.058859,-0.004857,-0.005291,-0.008349,0.007895,-0.020997,0.038854,-0.008349,0.016616,-0.060843,0.040507,0.021824,0.002253,-0.012565,0.006324,0.040011,0.073078,-0.02943,0.014384,-0.031083,0.010995,-0.025131,0.009011,0.015707,0.060182,0.05919,0.017443,0.033563,-0.039184,0.051915,0.040011,-0.021493,0.036208,-0.030091,0.022981,0.056214,0.070432,-0.004071,-0.019013,-0.000377,0.014549,-0.044971,-0.019592,0.013392,0.008308,-0.002563,-0.032902,0.001405,0.013061,0.013061,-0.018269,0.022155,-0.038358,0.048608,0.078699,-0.023477,-0.031744,-0.008308,-0.042326,0.015045,0.072086,0.010333,-0.058859,0.001467,0.040011,-0.011243,0.045302,-0.028107,-0.012731,0.056875,-0.003265,-0.015541,0.007771,0.030091,-0.057206,-0.014632,0.020667,-0.041995,0.030752,0.014053,-0.038027,0.013061,0.012565,0.002366,0.049931,-0.02976,0.015045,0.007564,-0.015459,0.04464,0.005745,-0.029099,-0.013557,-0.005869,0.024304,-0.026784,0.007688,-0.073078,-0.046624,-0.00155,0.000107,0.009259,-0.022155,0.015376,0.003885,-0.080352,0.011408,-0.020749,-0.01612,0.011573,0.055222,0.013557,0.00155,0.000961,0.012069,0.002955,-0.014797,-0.041499,-0.018683,-0.035216,-0.043648,0.103169,-0.007688,-0.024965,-0.005911,-0.012483,-0.024635,0.033398,-0.014053,0.015872,0.013723,0.000314,0.033728,-0.020088,0.016947,-0.061504,-0.046624,0.07407,-0.009383,0.001602,-0.040507,-0.071424,0.000899,-0.010127,-0.024635,-0.005828,0.03968,0.021989,-0.001684,-0.028272,0.035216,-0.046294,-0.002614,-0.027941,-0.020667,0.016368,0.001157,0.005952,0.007523,0.017195,0.038027,0.004402,-0.004505,0.057536,0.042987,-0.028438,-0.033728,0.010747,-0.004629,0.026123,0.014219,-0.003245,-0.028107,0.060182,0.03439,0.016947,-3.8e-05,-0.005229,0.013144,0.042987,0.007275,-0.028768,-0.000734,-0.002687,0.030091,-0.01488,-0.027611,-0.012813,-0.015707,-0.023477,0.001509,0.028934,-0.015376,0.000372,0.005456,-0.041334,0.032571,-0.030422,0.009837,-0.054891,-0.016368,0.005497,0.03224,-0.012648,-0.038027,0.002056,-0.035216,-0.017029,-0.046955,0.035712,0.019013,-0.023477,-0.033894,0.005787,0.021493,0.011491,0.0248,0.026288,0.035712,-0.031248,0.012896,0.025627,0.046955,-0.047947,-0.076054,0.054891,-0.045632,5.1e-05,0.006613,-0.003761,-0.021659,-0.038854,0.031414,-0.028438,-0.013061,-0.05952,-0.01612,-0.018021,0.002997,0.003038,-0.047286,-0.015376,-0.021163,-0.016285,-0.002893,-0.011656,0.021659,0.024469,0.01612,0.09391,0.030918,0.009672,-0.021659,0.056214,-0.04431,0.021824,-0.011325,0.014384,-0.0248,0.043318,0.005249,-0.010664,0.030422,0.060182,-0.006903,-0.038854,-0.000153,0.007936,-0.032075,0.008473,-0.008473,0.021989,0.020749,0.020667,-0.016037,-0.016781,-0.004898,0.00744,0.020088,0.026784,0.020088,0.005022,-0.036208,-0.00186,-0.006861,0.005663,-0.014797,0.052907,-0.013723,0.04431,-0.001963,0.043318,-0.006365,0.002501,-0.011987,0.024304,0.010375,-0.017608,-0.033728,0.018517,0.00092,0.002687,-0.004629,-0.002015,0.041499,0.010664,0.048278,0.011573,-0.065142,0.029926,0.018352,0.007812,-0.03439,0.019592,0.026784,0.0496,-0.007688,0.006531,-0.001457,0.0124,0.016285,0.004505,-0.014963,-0.030091,-0.07936,0.001602,0.013144,-0.026288,-0.00062,0.000297,-0.001225,-0.011408,-0.0124,0.007027,-0.004009,-0.003968,0.029926,0.007895,0.033563,0.013061,0.006696,0.009507,-0.009796,0.05456,-0.048608,0.006076,0.032902,-0.020667,-0.002914,0.000925,0.05423,0.011077,-0.036208,0.008845,-0.030752,-0.05919,0.04431,0.037035,-0.009011,-0.020749,0.007647,0.033894,-0.052246,0.037862,0.041334,0.019344,-0.075723,-0.004795,-0.000889,-0.011325,-0.006944,0.036539,0.021163,0.015211,0.075723,-0.02976,-0.022816,-0.027445,-0.014797,0.068779,0.03472,0.107137,-0.03439,-0.001059,-0.013723,-0.023973,0.046955,-0.000853,-0.05456,-0.025957,-0.044971,-0.0496,0.048608,-0.014219,0.010499,-0.015376,-0.026784,-0.023477,0.042326,0.018104,0.018517,0.046955,0.018269,-0.02976,0.028934,-0.031579,-0.009713,0.010747,-0.023477,0.062496,0.046624,-0.042987,0.070763,0.004898,-1.1e-05,-0.03439,0.001953,0.001788,0.016781,-0.02232,0.028768,0.044971,0.028768,-0.00868,-0.037035,0.001498,-0.02728,-0.006985,0.011656,-0.013557,0.010664,-0.052576,-0.026619,0.002645,0.021328,-0.009383,0.007688,-0.026619,0.045963,-0.037862,-0.024139,0.06448,-0.060843,0.045302,0.070432,-0.013805,0.023973,-0.066795,0.095233,0.006159,0.009011,0.04183,-0.065142,0.026123,-0.007068,-0.02232,0.016947,0.038027,0.014384,0.015211,-0.050262,0.038358,-0.008804,0.021659,0.03439,0.023973,0.00248,0.023477,0.002366,-0.003451,0.002459,0.095894,0.004898,-0.001059,0.034886,0.006944,0.005993,0.05952,-0.021328,0.005373,-0.037035,-0.001297,0.051584,-0.0496,0.028934,0.018021,0.042987,0.003989,-0.03191,0.043318,0.036043,0.017029,0.009383,-0.001405,-0.084651,-0.003079,-0.011325,0.004175,0.01488,-0.012483,0.041995,-0.018765,-0.011243,-0.001591,0.024635,0.01984,0.006241,0.009383,0.003761,0.04927,0.011325,0.020667,-0.022816,-0.0496,-0.014715,0.028107,0.001225,0.012152,-0.013888,-0.058198,0.03935,0.024635,0.072416,-0.048939,0.020336,0.015128,0.004237,-0.008597,0.031414,-0.040507,-0.018765,-0.011325,0.056544,0.029595,0.001044,-0.015789,0.05423,0.032902,-0.0031,-0.010333,-0.022816,-0.025461,0.006241,-0.000273,-0.011987,-0.038027,-0.061174,0.003865,-0.02943,0.012731,0.06448,-0.040507,0.011408,0.047947,0.015128,-0.011739,0.021659,0.012069,0.020997,-0.011325,0.003637,0.014549,-0.015045,0.011077,-0.008184,0.005869,-0.037862,-0.000806,0.018517,0.028603,0.00992,-0.000245,0.005249,-0.005084,-0.000692,-0.00094,-0.019179,-0.000625,-0.009135,-0.002811,-0.018104,-0.060182,-0.0248,0.000605,0.017856,0.005022,-0.017443,0.014384,-0.010127,-0.007523,0.041003,0.033563,-0.037366,0.003927,0.00806,-0.048278,0.016533,-0.021989,-0.009176,0.019013,0.022485,-0.005332,-0.026123,-0.014632,0.023973,-0.022155,0.016947,-0.020088,0.008184,-0.021493,0.027941,0.073408,0.03224,0.018104,-0.01736,-0.007275,0.031414,-0.007357,-0.04464,0.045302,-0.010664,-0.016203,0.010375,0.004567,0.0124,-0.009011,-0.010457')
 
    # Example 2: Perform similarity search in the Vector Store when question is stored in a table and output
    #            should be returned in 'json' format.
    >>> load_data("amazon", "amazon_review_query")
    >>> response = vs.similarity_search_by_vector(data="amazon_review_query",
                                                  column="queryEmbedding",
                                                  return_type="json")