Q i9:ddlZddlmZmZmZmZmZmZddlm Z m Z m Z m Z ddl mZmZddlmZddlmZddlmZddlmZdd lmZdd lmZed Zed ZGd de ZGddeZGddeZ GddeZ!dS)N)AnyDictListOptionalSetUnion) BaseModelFieldfield_validatormodel_validator)AggregateRequestDesc)Self)FilterExpression)array_to_buffer)VectorDataType)FullTextQueryHelper) lazy_importnltkznltk.corpus.stopwordsc:eZdZUdZeeeefed<e ed<dZ e ed<dZ eed<e dd d Z eed <edede d e fd Zed ed ed efdZedd efdZdS)Vectora Simple object containing the necessary arguments to perform a multi vector query. Args: vector: The vector values as a list of floats or bytes field_name: The name of the vector field to search dtype: The data type of the vector (default: "float32") weight: The weight for this vector in the combined score (default: 1.0) max_distance: The maximum distance for vector range search (default: 2.0, range: [0.0, 2.0]) vector field_namefloat32dtypeg?weight@)defaultgele max_distancereturnc t|n2#t$r%td|ddtDwxYw|S)NzInvalid data type: z. Supported types are: c6g|]}|S)lower).0ts C:\Users\Dell Inspiron 16\Desktop\tws\AgrotaPowerBi\back-agrota-powerbi\mcp-client-agrota\venv\Lib\site-packages\redisvl/query/aggregate.py z)Vector.validate_dtype..+s!DgDgDgSTQWWYYDgDgDg)rupper ValueError)clsrs r*validate_dtypezVector.validate_dtype$sw  5;;== ) ) ) )   ieiiDgDgXfDgDgDgii   s !$/Act|ttfstd|dks|dkrtd|S)Nz0max_distance must be a value between 0.0 and 2.0rr) isinstancefloatintr.)r/r"s r*validate_max_distancezVector.validate_max_distance/sT, 55 QOPP P #  !3!3OPP Pr,after)modec|t|jtr|St|j|j|_|S)zIIf the vector passed in is an array of float convert it to a byte string.)r2rbytesrrselfs r*validate_vectorzVector.validate_vector8s7 dk5 ) ) K%dk4:>>  r,N)__name__ __module__ __qualname____doc__rrr3r9__annotations__strrrr r"r classmethodr0r5r rr<r&r,r*rrs?   $u+u$ %%%%OOOE3FE%<<r?r@rH __classcell__rJs@r*rErEAsB'''''''''r,rEceZdZUdZdZeed<dZeed< d"d ededee e e fdedede eee fde dedede e ede eeeefdede eee fffd ZedeeeffdZedeefdZedeee ffdZdeee ffdZdefd Zdefd!ZxZS)#AggregateHybridQuerya AggregateHybridQuery combines text and vector search in Redis. It allows you to perform a hybrid search using both text and vector similarity. It scores documents based on a weighted combination of text and vector similarity. .. code-block:: python from redisvl.query import AggregateHybridQuery from redisvl.index import SearchIndex index = SearchIndex.from_yaml("path/to/index.yaml") query = AggregateHybridQuery( text="example text", text_field_name="text_field", vector=[0.1, 0.2, 0.3], vector_field_name="vector_field", text_scorer="BM25STD", filter_expression=None, alpha=0.7, dtype="float32", num_results=10, return_fields=["field1", "field2"], stopwords="english", dialect=2, ) results = index.query(query) vector_distance DISTANCE_IDr VECTOR_PARAMBM25STDNffffff?r englishtexttext_field_namevector_field_name text_scorerfilter_expressionalphar num_results return_fields stopwordsdialect text_weightsc|std||_||_||_||_||_||_||_| |_ t| | |_ | }t|||||d|jdd|d|z d|d  |t)d | || | r |j| d Sd S)a Instantiates a AggregateHybridQuery object. Args: text (str): The text to search for. text_field_name (str): The text field name to search in. vector (Union[bytes, List[float]]): The vector to perform vector similarity search. vector_field_name (str): The vector field name to search in. text_scorer (str, optional): The text scorer to use. Options are {TFIDF, TFIDF.DOCNORM, BM25, DISMAX, DOCSCORE, BM25STD}. Defaults to "BM25STD". filter_expression (Optional[FilterExpression], optional): The filter expression to use. Defaults to None. alpha (float, optional): The weight of the vector similarity. Documents will be scored as: hybrid_score = (alpha) * vector_score + (1-alpha) * text_score. Defaults to 0.7. dtype (str, optional): The data type of the vector. Defaults to "float32". num_results (int, optional): The number of results to return. Defaults to 10. return_fields (Optional[List[str]], optional): 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. dialect (int, optional): The Redis dialect version. Defaults to 2. 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. Note: AggregateHybridQuery uses FT.AGGREGATE commands which do NOT support runtime parameters. For runtime parameter support (ef_runtime, search_window_size, etc.), use VectorQuery or VectorRangeQuery which use FT.SEARCH commands. Raises: ValueError: If the text string is empty, or if the text string becomes empty after stopwords are removed. TypeError: If the stopwords are not a set, list, or tuple of strings. ztext string cannot be empty)r_raz(2 - @)/2z@__score)vector_similarity text_scorez*@text_score + z*@vector_similarity) hybrid_scorez @hybrid_scoremaxN)stripr._text _text_field_vector _vector_field_filter_expression_alpha_dtype _num_resultsr _ft_helper_build_query_stringrGrHscorer add_scoresapplyrPsort_byrr`load)r;rWrXrrYrZr[r\rr]r^r_r`rarIrJs r*rHzAggregateHybridQuery.__init__mszvzz|| <:;; ; * ."3  '-%    //11  &&& K     []) rsbuild_query_stringrkrlrorrrnrQrP)r;rW knn_querys r*rtz(AggregateHybridQuery._build_query_strings11 J($*A   R4$ Q Q(: Q Qd>O Q Q  .D,... ''9''''r,cddd|DS).Return the string representation of the query. c,g|]}t|Sr&rBr(xs r*r+z0AggregateHybridQuery.__str__..;;;AQ;;;r,join build_argsr:s r*__str__zAggregateHybridQuery.__str__-xx;;):):;;;<<r?r@rPrBrArQrr9rr3rrr4rrrHpropertyrr}r_rarrtrrKrLs@r*rNrNJsM>)K((( L#   %DH-14=37X&X&X&X&eT%[() X&  X&  X&$E#/?*?$@AX&X&X&X& S *X&E#s3x-01X&X&tCJ/0X&X&X&X&X&X&t S#X   X )3s8)))X),d3:.,,,X,1S%Z(81111(S(((( =========r,rNc eZdZUdZeeed< ddeeeefdeee deee e fd e d e f fd Z e d ee effd Zd e fdZd e fdZxZS)MultiVectorQueryaJ MultiVectorQuery allows for search over multiple vector fields in a document simultaneously. The final score will be a weighted combination of the individual vector similarity scores following the formula: score = (w_1 * score_1 + w_2 * score_2 + w_3 * score_3 + ... ) Vectors may be of different size and datatype, but must be indexed using the 'cosine' distance_metric. .. code-block:: python from redisvl.query import MultiVectorQuery, Vector from redisvl.index import SearchIndex index = SearchIndex.from_yaml("path/to/index.yaml") vector_1 = Vector( vector=[0.1, 0.2, 0.3], field_name="text_vector", dtype="float32", weight=0.7, ) vector_2 = Vector( vector=[0.5, 0.5], field_name="image_vector", dtype="bfloat16", weight=0.2, ) vector_3 = Vector( vector=[0.1, 0.2, 0.3], field_name="text_vector", dtype="float64", weight=0.5, ) query = MultiVectorQuery( vectors=[vector_1, vector_2, vector_3], filter_expression=None, num_results=10, return_fields=["field1", "field2"], dialect=2, ) results = index.query(query) _vectorsNrTrVvectorsr^r[r]r`c  ||_||_t|tr |g|_n||_t d|jDst d|}t |tt|jD]}|j did|d|dig}td|jDD] \}} |d|d| !d |} | | |t#d | |||r |j|d Sd S)a@ Instantiates a MultiVectorQuery object. Args: vectors (Union[Vector, List[Vector]]): The Vectors to perform vector similarity search. return_fields (Optional[List[str]], optional): The fields to return. Defaults to None. filter_expression (Optional[Union[str, FilterExpression]]): The filter expression to use. Defaults to None. num_results (int, optional): The number of results to return. Defaults to 10. dialect (int, optional): The Redis dialect version. Defaults to 2. c8g|]}t|tSr&)r2rr(vs r*r+z-MultiVectorQuery.__init__..Ss"AAAaJq&))AAAr,zBvector argument must be a Vector object or list of Vector objects.score_z(2 - @distance_rccg|] }|j Sr&)rrs r*r+z-MultiVectorQuery.__init__..as???Aqx???r,z@score_z * z + )combined_scorez@combined_scorerhNr&)rorrr2rrall TypeErrorrtrGrHrangelenrw enumerateappendrrxrr`ry) r;rr^r[r]r`rIicombined_scoreswcombined_score_stringrJs r*rHzMultiVectorQuery.__init__7s(#4' gv & & $$IDMM#DMAA4=AAABB T //11  &&&s4=))** C CA DJ B B,1,,(@!(@(@(@A B B B B?????@@ 8 8DAq  " "#6Q#6#61#6#6 7 7 7 7 % ? ; ; "7 888 T+,,+ >>> W  & DI} % % % % & &r,r#cXi}t|jD]\}}|j|d|<|S)r{vector_)rrr)r;r}rrs r*r}zMultiVectorQuery.paramsls@dm,, - -DAq$%HF=Q== ! ! r,c Jg}td|jDD]+\}\}}}|d|d|d|d|d ,d|}|j}t |jt rt|j}|r d|d |d S|S) rc6g|]}|j|j|jfSr&)rrr"rs r*r+z8MultiVectorQuery._build_query_string..~s% M M M!ah an 5 M M Mr,@z:[VECTOR_RANGE z $vector_z!]=>{$YIELD_DISTANCE_AS: distance_}z AND (z) AND ())rrrrror2rrB)r; range_queriesrrfieldmax_dist range_queryr[s r*rtz$MultiVectorQuery._build_query_stringxs ,5 M Mt} M M M- -    (A(x  gEgg(ggQggbcggg    ll=11  3 d-/? @ @ = #D$; < <   $?{??+<??? ?!# #r,cddd|DS)rrc,g|]}t|Sr&rrs r*r+z,MultiVectorQuery.__str__..rr,rr:s r*rzMultiVectorQuery.__str__rr,)NNrTrV)r=r>r?r@rrrArrrBrr4rHrrrr}rtrrKrLs@r*rrs,,,\6l .2DH 3&3&vtF|+,3& S *3&$E#/?*?$@A 3&  3&  3&3&3&3&3&3&j S#X   X $S$$$$.=========r,r)"warningstypingrrrrrrpydanticr r r r !redis.commands.search.aggregationr rtyping_extensionsrredisvl.query.filterrredisvl.redis.utilsrredisvl.schema.fieldsr$redisvl.utils.full_text_query_helperrredisvl.utils.utilsrrnltk_stopwordsrrErNrr&r,r*rs8888888888888888GGGGGGGGGGGGDDDDDDDD""""""111111//////000000DDDDDD++++++{6455,,,,,Y,,,^'''''''''y=y=y=y=y=+y=y=y=xK=K=K=K=K='K=K=K=K=K=r,