Q ih@ddlmZmZmZmZmZmZmZddlm Z ddl m Z ddl m Z ddlmZdZGddZ d d ed ed ededeedeeddeedeedeedeedeedeeee ffdZ d!deddeedeedeedeef dZd S)")AnyDictListLiteralOptionalSetUnion)Filter)FilterExpression)array_to_buffer)FullTextQueryHelperz9Hybrid queries require Redis >= 8.4.0 and redis-py>=7.1.0c2eZdZdZ d%d ed edeeeefdededede ede e dde de edede ede eee fde e dde de dede eded e e d!e eed"e eee efd#e eeeff.d$ZdS)& HybridQuerya A hybrid search query that combines text search and vector similarity, with configurable fusion methods. .. code-block:: python from redisvl.query import HybridQuery from redisvl.index import SearchIndex index = SearchIndex.from_yaml("path/to/index.yaml") query = HybridQuery( text="example text", text_field_name="text_field", vector=[0.1, 0.2, 0.3], vector_field_name="vector_field", text_scorer="BM25STD", yield_text_score_as="text_score", yield_vsim_score_as="vector_similarity", combination_method="LINEAR", linear_alpha=0.3, yield_combined_score_as="hybrid_score", num_results=10, return_fields=["field1", "field2"], stopwords="english", ) results = index.query(query) See Also: - `FT.HYBRID command documentation `_ - `redis-py hybrid_search documentation `_ vectorBM25STDN {Gz?<333333?float32englishtexttext_field_namevector_field_namevector_param_name text_scoreryield_text_score_asvector_search_methodKNNRANGEknn_ef_runtime range_radius range_epsilonyield_vsim_score_asfilter_expressioncombination_methodRRFLINEAR rrf_window rrf_constant linear_alphayield_combined_score_asdtype num_results return_fields stopwords text_weightscJ ddlm}m}n)#ttf$rtt wxYw||_|r|jd||r|jjd|Dt|||_ |j ||| }t|tr|}nt||}||i|_t!|||||||| | | | |  |_|rt%||||||_dSd|_dS) a> Instantiates a HybridQuery object. Args: text: The text to search for. text_field_name: The text field name to search in. vector: The vector to perform vector similarity search. vector_field_name: The vector field name to search in. vector_param_name: The name of the parameter substitution containing the vector blob. text_scorer: The text scorer to use. Options are {TFIDF, TFIDF.DOCNORM, BM25STD, BM25STD.NORM, BM25STD.TANH, DISMAX, DOCSCORE, HAMMING}. Defaults to "BM25STD". For more information about supported scoring algorithms, see https://redis.io/docs/latest/develop/ai/search-and-query/advanced-concepts/scoring/ yield_text_score_as: The name of the field to yield the text score as. vector_search_method: The vector search method to use. Options are {KNN, RANGE}. Defaults to None. knn_ef_runtime: The exploration factor parameter for HNSW, optional if `vector_search_method` is "KNN". range_radius: The search radius to use, required if `vector_search_method` is "RANGE". range_epsilon: The epsilon value to use, optional if `vector_search_method` is "RANGE"; defines the accuracy of the search. yield_vsim_score_as: The name of the field to yield the vector similarity score as. filter_expression: The filter expression to use for both the text and vector searches. Defaults to None. combination_method: The combination method to use. Options are {RRF, LINEAR}. If not specified, the server defaults to RRF. If "RRF" is specified, then at least one of `rrf_window` or `rrf_constant` must be provided. If "LINEAR" is specified, then at least one of `linear_alpha` or `linear_beta` must be provided. rrf_window: The window size to use for the reciprocal rank fusion (RRF) combination method. Limits fusion scope. rrf_constant: The constant to use for the reciprocal rank fusion (RRF) combination method. Controls decay of rank influence. linear_alpha: The weight of the text query for the linear combination method (LINEAR). yield_combined_score_as: The name of the field to yield the combined score as. dtype: The data type of the vector. Defaults to "float32". num_results: The number of results to return. return_fields: The fields to return. Defaults to None. stopwords (Optional[Union[str, Set[str]]], optional): The stopwords to remove from the provided text prior to search-use. If a string such as "english" "german" is provided then a default set of stopwords for that language will be used. if a list, set, or tuple of strings is provided then those will be used as stopwords. Defaults to "english". if set to "None" then no stopwords will be removed. Note: This parameter controls query-time stopword filtering (client-side). For index-level stopwords configuration (server-side), see IndexInfo.stopwords. Using query-time stopwords with index-level STOPWORDS 0 is counterproductive. text_weights (Optional[Dict[str, float]]): The importance weighting of individual words within the query text. Defaults to None, as no modifications will be made to the text_scorer score. Raises: ImportError: If redis-py>=7.1.0 is not installed. TypeError: If the stopwords are not a set, list, or tuple of strings. ValueError: If the text string is empty, or if the text string becomes empty after stopwords are removed. ValueError: If `vector_search_method` is defined and isn't one of {KNN, RANGE}. ValueError: If `vector_search_method` is "KNN" and `knn_k` is not provided. ValueError: If `vector_search_method` is "RANGE" and `range_radius` is not provided. r)CombineResultsMethodHybridPostProcessingConfig)offsetnumc3 K|] }d|V dS)@N).0fs C:\Users\Dell Inspiron 16\Desktop\tws\AgrotaPowerBi\back-agrota-powerbi\mcp-client-agrota\venv\Lib\site-packages\redisvl/query/hybrid.py z'HybridQuery.__init__..s(-M-M!g!gg-M-M-M-M-M-M)r3r4) text_queryrrrrrr1r#r$r%r&r')r(r,r-r.yield_score_asN)"redis.commands.search.hybrid_queryr6r7 ImportErrorModuleNotFoundError_IMPORT_ERROR_MESSAGEpostprocessing_configlimitloadr _ft_helperbuild_query_string isinstancebytesr paramsbuild_base_queryquerybuild_combination_methodr()selfrrrrrrrrr#r$r%r&r'r(r,r-r.r/r0r1r2r3r4r6r7 query_string vector_datas r?__init__zHybridQuery.__init__.sd 5         01 5 5 5344 4 5&@%?%A%A"  H  & , ,A; , G G G  O +D & +-M-M}-M-M-M N N-%    99 /#4   fe $ $ 9 KK)&%88K {  &#//# 3!5#)%' 3/       +('9)!-!-#:   # # #'+D # # # &1)rrNNrNrNNNrrrNrrNrN)__name__ __module__ __qualname____doc__strr rNrfloatrrintr rrrVr<rAr?rr sN"*$-1BF (,#-1DHAE!15%'-14=371L+L+L+L+eT%[() L+  L+  L+L+&c]L+'w~'>?L+L+uoL+L+&c]L+$E#/?*?$@AL+%W_%=>L+ !L+"#L+$%L+&"*#'L+()L+*c]+L+, S *-L+.E#s3x-01/L+0tCJ/01L+L+L+L+L+L+rArrNrBrrrrrr r1r#r$r%r&r'c P ddlm} ddlm} m}m}n)#t t f$rt twxYw| |||}d}i}|dkr%|j}|std||d<|r||d <n?|d kr%|j }|std ||d <| r| |d <n|td|t| trt| } | r$| dkrtdt| }nd}|d|zd|z|||| }| ||S)aqBuild a Redis HybridQuery for performing hybrid search. Args: text_query: The query for the text search. vector_param_name: The name of the parameter substitution containing the vector blob. vector_field_name: The vector field name to search in. text_scorer: The text scorer to use. Options are {TFIDF, TFIDF.DOCNORM, BM25STD, BM25STD.NORM, BM25STD.TANH, DISMAX, DOCSCORE, HAMMING}. Defaults to "BM25STD". For more information about supported scroring algorithms, see https://redis.io/docs/latest/develop/ai/search-and-query/advanced-concepts/scoring/ yield_text_score_as: The name of the field to yield the text score as. vector_search_method: The vector search method to use. Options are {KNN, RANGE}. Defaults to None. num_results: The number of nearest neighbors to return, required if `vector_search_method` is "KNN". knn_ef_runtime: The exploration factor parameter for HNSW, optional if `vector_search_method` is "KNN". range_radius: The search radius to use, required if `vector_search_method` is "RANGE". range_epsilon: The epsilon value to use, optional if `vector_search_method` is "RANGE"; defines the accuracy of the search. yield_vsim_score_as: The name of the field to yield the vector similarity score as. filter_expression: The filter expression to use for the vector similarity search. Defaults to None. Notes: If RRF combination method is used, then at least one of `rrf_window` or `rrf_constant` must be provided. If LINEAR combination method is used, then at least one of `linear_alpha` or `linear_beta` must be provided. Raises: ImportError: If redis-py>=7.1.0 is not installed. ValueError: If `vector_search_method` is defined and isn't one of {KNN, RANGE}. ValueError: If `vector_search_method` is "KNN" and `knn_k` is not provided. ValueError: If `vector_search_method` is "RANGE" and `range_radius` is not provided. Returns: A Redis HybridQuery object that defines the text and vector searches to be performed. r)r)HybridSearchQueryHybridVsimQueryVectorSearchMethods)rTscorerrCNr!z9Must provide `num_results` if vector_search_method is KNNK EF_RUNTIMEr"z4Must provide RADIUS if vector_search_method is RANGERADIUSEPSILONzUnknown vector search method: *FILTERr;$)rrUvsim_search_methodvsim_search_method_paramsfilterrC) search_queryvector_similarity_query)rDrr`rarbrErFrGr! ValueErrorr"rMr r\r )rBrrrrrr1r#r$r%r&r'RedisHybridQueryr`rarbrnrkrl vsim_filter vsim_querys r?rPrPs^1VVVVVV           , -111/0001%$*L9=02u$$04 K *5!#&  E6D %l 3  ( (06 USTT T.:!(+  A3@ %i 0  )P:NPPQQQ#%5663 122.#55Xs+<'='=>>  ! 11++-";* J  ! *   s&9r(r)r,r-r.rCcF ddlm}m}n)#ttf$rtt wxYwi}|dkr|j}|r||d<|r||d<n/|dkr|j}|r ||d<d|z |d <ntd ||r||d <|std |dd |i|S)aUBuild a configuration for combining hybrid search scores. Args: combination_method: The combination method to use. Options are {RRF, LINEAR}. rrf_window: The window size to use for the reciprocal rank fusion (RRF) combination method. Limits fusion scope. rrf_constant: The constant to use for the reciprocal rank fusion (RRF) combination method. Controls decay of rank influence. linear_alpha: The weight of the first query for the linear combination method (LINEAR). yield_score_as: The name of the field to yield the combined score as. Raises: ImportError: If redis-py>=7.1.0 is not installed. ValueError: If `combination_method` is defined and isn't one of {RRF, LINEAR}. ValueError: If `combination_method` is "RRF" and neither `rrf_window` nor `rrf_constant` is provided. ValueError: If `combination_method` is "LINEAR" and neither `linear_alpha` nor `linear_beta` is provided. Returns: A CombineResultsMethod object that defines how the text and vector scores should be combined. r)CombinationMethodsr6r*WINDOWCONSTANTr+ALPHABETAzUnknown combination method: YIELD_SCORE_ASzTNo parameters provided for combination method - must provide at least one parameter.methodr<) rDrur6rErFrGr*r+rp) r(r,r-r.rCrur6 method_paramsr|s r?rRrR/sP61          , -111/0001%'MU""#'  1&0M( #  5(4M* % x ' '#*  5%1M' "$% $4M& !L8JLLMMM9*8 &'   b          rW) rNNNNNNNN)NNNN)typingrrrrrrr redis.commands.search.queryr redisvl.query.filterr redisvl.redis.utilsr $redisvl.utils.full_text_query_helperr rGrr\r^r]rPrRr<rAr?rsAAAAAAAAAAAAAAAAAA......111111//////DDDDDDSn+n+n+n+n+n+n+n+j!)->B!%$($(%))-@Dooooo o "# o #7>#:; o#oSMo5/oE?o"#o c+;&; <=ooooh!%$($($( ??0? ?5/?5/ ? SM ??????rA