dh|aSSKJr SSKrSSKrSSKrSSKrSSKJrJrJ r J r J r J r J r SSKrSSKJr SSKJr SSKJr SSKJr SSKJr S rSS jrSS jr"S S \5rg)) annotationsN)AnyCallableDictIterableListOptionalType)Document) Embeddings guard_import) VectorStore)maximal_marginal_relevancec[S5$)zImport lancedb package.lancedbr `/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/lancedb.pyimport_lancedbrs  ""rc SRUR5VVs/sH upUSUS3PM snn5$s snnf)z2Converts a dict filter to a LanceDB filter string.z AND z = '')joinitems)filterkvs rto_lance_filterrs7 <"> ? ?)   S'***?*?$@ A A8  ||##*??3#7 c3''~~g..+2??dkk,;,(,3??3+?( =   !GJJ117>>3G3G3S3ST$ ")%"8"8EJJn ...FDK "  @ s 7A1J??KcjURRnSU;aSnO SU;aSnOSnSU;nUbU(df[[U55Vs/sHGn[ XR UR 5U(aUSUR 5O0S9PMI sn$U(aU(a{[[U55Vs/sH\n[ XR UR 5U(aUSUR 5O0S9XUR 54PM^ sn$ggs snfs snf)N _distance_relevance_scoremetadata) page_contentra)schemanamesrangelenr r6as_py)rRresultsscorecolumns score_col has_metadataidxs rresults_to_docsLanceDB.results_to_docssF..&& ' !#I 7 **II!W,  E !W.  /C !(!8!=!C!C!EAMWZ05;;=SU/  5!W. /C%,^^%dictrgetsearchr4rwhererArerankto_arrowrfrJrK) rRrrrr.rrrrr lance_queryrs r_queryLanceDB._queryls% 9 AnnT" fd # #$V,FJJ{E2 ZZ h7 jj+ +7 + ;K;K Lqv3  ;K;K Lqv3   !dnn&@     7##% t9> MM; < rcUR(a UR$URS:Xa UR$URS:Xa UR$URS:Xa UR$[ SURS35e)a The 'correct' relevance function may differ depending on a few things, including: - the distance / similarity metric used by the VectorStore - the scale of your embeddings (OpenAI's are unit normed. Many others are not!) - embedding dimensionality - etc. cosiner(ipzANo supported normalization function for distance metric of type: z=.Consider providing relevance_score_fn to Chroma constructor.)r;r:_cosine_relevance_score_fn_euclidean_relevance_score_fn%_max_inner_product_relevance_score_fnrBrqs r_select_relevance_score_fn"LanceDB._select_relevance_score_fns  + +33 3 ==H $22 2 ]]d "55 5 ]]d "== =115@OO rc Uc URnUR"X4X4S.UD6nURXeRSS5S9$)z4 Return documents most similar to the query vector. rr.riFri)r<rrnpop)rRrTrrr.rress rsimilarity_search_by_vector#LanceDB.similarity_search_by_vectorsI 9 Akk)KvKFK##Czz'5/I#JJrc Uc URnUR5nUR"X4SS0UD6nUVV s/sHupX"[U 554PM sn n$s sn nf)zJ Return documents most similar to the query vector with relevance scores. riT)r<rrfloat) rRrTrrr.rr[docs_and_scoresdocris r1similarity_search_by_vector_with_relevance_scores9LanceDB.similarity_search_by_vector_with_relevance_scoressz 9 A!<<>::  $ (. GV FU S$U5\2 3o   sAc Uc URnURSS5nURSS5nURSS5nURc [S5eUS:XdUS :XaURcUR c{UR U5nURURSS 9UlUS :XaURRU5n X4n OUn UR"X4X6S .UD6n URXS 9$[S 5eURRU5n UR"X4SU0UD6n URXS 9$)zAReturn documents most similar to the query with relevance scores.NriTr.rr#z4search needs an emmbedding function to be specified.ftsr)replacerrz?Full text/ Hybrid search is not supported in LanceDB Cloud yet.r) r<rr3rBr,r=rQcreate_fts_indexr6 embed_queryrrnNotImplementedError) rRrrrrrir.rrrTrrs rsimilarity_search_with_score$LanceDB.similarity_search_with_scoresJ 9 A 7D)zz&$'ZZ h7 ?? "ST T  *"8||#(?nnT*"%"6"6t~~t"6"T) $ ; ;E BI'/F"Fkk&PFPP++C+==)U33E:I++iD6DVDC'''9 9rc 4UR"SXX4USS.UD6nU$)aReturn documents most similar to the query Args: query: String to query the vectorstore with. k: Number of documents to return. filter (Optional[Dict]): Optional filter arguments sql_filter(Optional[string]): SQL filter to apply to the query. prefilter(Optional[bool]): Whether to apply the filter prior to the vector search. Raises: ValueError: If the specified table is not found in the database. Returns: List of documents most similar to the query. F)rrr.rrrir)r)rRrrr.rrrrs rsimilarity_searchLanceDB.similarity_searchs10// 4Cu PV  rc Uc URnURc [S5eURRU5nUR UUUUUS9nU$)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. zBFor MMR search, you must specify an embedding function oncreation.) lambda_multr)r<r3rBr'max_marginal_relevance_search_by_vector) rRrrfetch_krrrrTrs rmax_marginal_relevance_search%LanceDB.max_marginal_relevance_searchsm4 9 A ?? "T OO//6 ;;  # <  rc LUR"SUUUS.UD6n[[R"U[RS9USR 5U=(d UR US9nURU5n [U 5V V s/sHupX;dM U PM n n n U $s sn n f)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. )rrr)dtyper#)rrr) rrnparrayfloat32 to_pylistr<rnr{) rRrTrrrrrrh mmr_selected candidatesirselected_resultss rr/LanceDB.max_marginal_relevance_search_by_vectorCs6++     2 HHYbjj 1 H  ' ' )o4::#  ))'2 *3J*?U*?$!1CTA*?UVs  B B c T[SUUUUUUU U U U U US. UD6nURXS9 U$)N) rSrTrVrWrXrYr,r-r9r:rZr[)rr)r!r)clsrrTrrSrVrWrXrYr,r-r9r:rZr[rinstances r from_textsLanceDB.from_textspsY& !!!1   56rc URU5nU(aURU5 gU(a=URURS3RSR U555 gU(a*UR b [ S5eURU5 gU(aURS5 g[S5e)aP Allows deleting rows by filtering, by ids or drop columns from the table. Args: filter: Provide a string SQL expression - "{col} {operation} {value}". ids: Provide list of ids to delete from the table. drop_columns: Provide list of columns to drop from the table. delete_all: If True, delete all rows from the table. z in ('{}'),Nz;Column operations currently not supported in LanceDB Cloud.truez6Provide either filter, ids, drop_columns or delete_all) rQdeleter5formatrr,r drop_columnsrB)rRr delete_allrrr.rrs rrLanceDB.deletes$nnT"  JJv   JJ$,,|4;;CHHSMJ K ||')Q  .  JJv UV Vr)rGr3r=r5rArMrOr6r4r,r:r<r9r;r-)rS Optional[Any]rTOptional[Embeddings]rU Optional[str]rVrrWrrXrrYrr,rr-rr9rr2rr:rrZrr["Optional[Callable[[float], float]]r<int)F)rhrriboolreturnr)rr)NN) rz Iterable[str]rOptional[List[dict]]rOptional[List[str]]rrr List[str])NF)r.rr0Optional[bool]rr)NN`NL2N)rrrrr Optional[int]rrrrrrr.rrNone)rUrCrrC) rrrrrrrrrr)NNN) rrrrrrr.rrrrr)rzCallable[[float], float]) rT List[float]rrrOptional[Dict[str, str]]r.rrrrr) rrCrrrrrrrr)NNNF)rrCrrr.rrrrrrrrList[Document])Ng?N)rrCrrrrrrrrrrrr )rTrrrrrrrrrrrrr ) NNr#r$r%r&NNr'r(NN)"rz Type[LanceDB]rrrTr rrrSrrVrrWrrXrrYrr,rr-rr9rr:rrZrr[rrrrr!)NNNNN)rrrrrrrrr.rrrrr)__name__ __module__ __qualname____firstlineno____doc__ DEFAULT_Kr\rnpropertyrrrrQrrrrrrrrrrr classmethodrr__static_attributes__rrrr!r!s:%)*.+$, $"($1!% $)#"&"&AE!VG!VG(VG VG " VG  VG VG"VGVGVGVGVG VG VG?VG !VGp D +/#' ..(.! .  .  .bIN!7E F#'$((+)+*. $"(F(F"(F& (F ' (F ( (F(F(F (FTG+/#' 22(2! 2  2  2n $" $$ $ $  $  $ $L8 +/" KK K) K  K  K K( +/"     )        2 +/ &:&: &:) &:  &: &:V " $#        @  +/ ** * *  * ) ** *^  +/ + +  +  +  + ) + +  + Z +/$($, $"($1!% $)"&"&AE# ###( # " # " ## #"#### # #?# !#" ###N$(%) $,0" !W !W#!W !W * !W  !W!W !W!Wrr!)rr)rzDict[str, str]rrC) __future__rrr7rwrJtypingrrrrrr r numpyrlangchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsrlangchain_core.vectorstoresr&langchain_community.vectorstores.utilsrrrrr!rrrrsO" FFF-0-3M # E Y WkY Wr