dhNjSSKJr SSKrSSKrSSKJr SSKJr SSKJ r J r J r J r J r JrJrJr SSKrSSKJr SSKJr SSKJr SS KJrJr SS KJr SS KJr \R@"5r!S r"SS jr#SSjr$SSjr%\ \&\\&\'\(\)44r*"SS\5r+"SS\5r,"SS\5r-SSjr.SSjr/g)) annotationsN)sha1)Thread)AnyDictIterableListMappingOptionalTupleUnion)Document) Embeddings) VectorStore) BaseSettingsSettingsConfigDict) TypedDict)maximal_marginal_relevanceFc$UH nX ;dM g g)z Check if a string has multiple substrings. Args: s: The string to check *args: The substrings to check for in the string Returns: bool: True if all substrings are present in the string, False otherwise FT)sargsas b/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/starrocks.pyhas_mul_sub_strrs : c2[(a [U5 gg)zK Print a debug message if DEBUG is True. Args: s: The message to print N)DEBUGprint)rs r debug_outputr &s  u a rc,UR5nURU5 URn/nUR5H5n0n[ U5HupxX7Sn XU 'M UR U5 M7 [ U5 UR5 U$)z Get a named result from a query. Args: connection: The connection to the database query: The query to execute Returns: List[dict[str, Any]]: The result of the query r)cursorexecute descriptionfetchall enumerateappendr close) connectionqueryr"columnsresultvalueridxdatumks rget_named_resultr20s   F NN5  G F" #E*JC QAaD+  a #  LLN MrcH\rSrSr%S\S'S\S'S\S'S\S 'S \S 'S rg ) QueryResultLzList[List[str]]idsz List[Any] embeddingsList[Document] documentszOptional[List[Metadata]] metadataszOptional[List[float]] distancesrN)__name__ __module__ __qualname____firstlineno____annotations____static_attributes__rrrr4r4Ls ''$$rr4c\rSrSr%SrSrS\S'SrS\S'S rS\S 'S r S\S 'S SSSS.r S\S'Sr S\S'Sr S\S'S Sjr \"SSSSS9rSrg)!StarRocksSettingsTaStarRocks client configuration. Attribute: StarRocks_host (str) : An URL to connect to MyScale backend. Defaults to 'localhost'. StarRocks_port (int) : URL port to connect with HTTP. Defaults to 8443. username (str) : Username to login. Defaults to None. password (str) : Password to login. Defaults to None. database (str) : Database name to find the table. Defaults to 'default'. table (str) : Table name to operate on. Defaults to 'vector_table'. column_map (Dict) : Column type map to project column name onto langchain semantics. Must have keys: `text`, `id`, `vector`, must be same size to number of columns. For example: .. code-block:: python { 'id': 'text_id', 'embedding': 'text_embedding', 'document': 'text_plain', 'metadata': 'metadata_dictionary_in_json', } Defaults to identity map. localhoststrhostiF#intportrootusernamepasswordiddocument embeddingmetadata)rNrOrPrQzDict[str, str] column_mapdefaultdatabase langchaintablec[X5$N)getattr)selfitems r __getitem__StarRocksSettings.__getitem__s t""rz.envutf-8 starrocks_ignore)env_fileenv_file_encoding env_prefixextrarN)r[rFreturnr)r<r=r>r?__doc__rGr@rIrKrMrRrTrVr\r model_configrArrrrCrCTs6D#D#HcHc  "JHcE3#&! LrrCc^\rSrSrSrSSU4SjjjrSSjr\SSj5rSSjr SSjr SSSjjr \ SSS jj5r SS jrSSS jjrS S!S jjrS S"S jjrS S#SjjrS$Sjr\SSj5rS%S&SjjrS'S(SjjrSrU=r$)) StarRocksa`StarRocks` vector store. You need a `pymysql` python package, and a valid account to connect to StarRocks. Right now StarRocks has only implemented `cosine_similarity` function to compute distance between two vectors. And there is no vector inside right now, so we have to iterate all vectors and compute spatial distance. For more information, please visit [StarRocks official site](https://www.starrocks.io/) [StarRocks github](https://github.com/StarRocks/starrocks) c >SSKnSSKJn XPl[TU]5 UbX lO[5UlUR (deUR R(aUR R(deUR R(a6UR R(aUR R(deSHnX`R R;aMe [URS55nSUR RS UR RS UR RS S UR RS S UR RSSUR RSS3 UlXplSUlSUlXlSUl[+UR 5 UR,"SUR RUR RUR R.UR R0UR RS.UD6Ul[+UR5 [5UR2UR5 g![a [S5ef=f![a SUlGNf=f)zStarRocks Wrapper to LangChain embedding_function (Embeddings): config (StarRocksSettings): Configuration to StarRocks Client rNzVCould not import pymysql python package. Please install it with `pip install pymysql`.)tqdmcU$rXr)xkwargss r$StarRocks.__init__..sQr)rNrPrOrQtestzCREATE TABLE IF NOT EXISTS .z ( rNz string, rOrPz array, rQzf string ) ENGINE = OLAP PRIMARY KEY(id) DISTRIBUTED BY HASH(id) PROPERTIES ("replication_num" = "1")\)rt'DESC)rGrIuserrMrTr)pymysql ImportErrorrlpgbarsuper__init__configrCrGrIrRrTrVlen embed_queryschemadimBS must_escapeembedding_function dist_orderr connectrKrMr)r2) rZrPr}rorxrlr1r __class__s rr|StarRocks.__init__sQ    / !J    K+-DK{{{{{DKK$4$444{{%%$++*>*>4;;CTCTTT# UH&oTR;aTRU3OUv M( g7frX)rr).0crZs r 'StarRocks.escape_str..s/VPU1t/?/?*?$''1#QFPUs-0)join)rZr-s` r escape_strStarRocks.escape_strswwVPUVVVrcUR$rX)rrZs rr7StarRocks.embeddingss&&&rc SRU5n[U5RURRS5n/nUHunSR[ U5VVs/sH6upxXt:waSUR [U55S3O S[U53PM8 snn5nURSUS35 Mw SURRSURRSUS SRU5S 3 n U $s snnf) N,rPruz array()z1 INSERT INTO rsz)) VALUES z ) rtupleindexr}rRr&rrFr'rTrV) rZtransac column_namesksembed_tuple_index_datanr/_ni_strs r_build_insert_sqlStarRocks._build_insert_sqls XXl #!,/55 KK " "; / A&/q\  &2 3DOOCG45Q7+CG956&2  A LL1QCq "[[))*!DKK,=,=+>atD%!"   !s#> *+d22 ,,-Qt{{/@/@.ABU doou 5A y7C 00@63P PE '%~Z@ @E *+d22 rcSR[[U55nU(aSU3nOSnSURRSSURRSSUS URRS S URRS S URR S URR SUSURSUS3n[U5 U$)NrzWHERE rLz? SELECT id as id, rOz as document, rQzC as metadata, cosine_similarity_norm(array[z], rPz) as dist, z as embedding FROM rsz z ORDER BY dist z LIMIT ) rrrFr}rRrTrVrr )rZq_embtopk where_str q_emb_strrs r_build_query_sqlStarRocks._build_query_sqlssHHSe_-   ,II'' 345'' 34555>K@'' 456'' 456++&&'q):):(;< K??+,&   U rc \UR"URRU5X#40UD6$)aKPerform a similarity search with StarRocks Args: query (str): query string k (int, optional): Top K neighbors to retrieve. Defaults to 4. where_str (Optional[str], optional): where condition string. Defaults to None. NOTE: Please do not let end-user to fill this and always be aware of SQL injection. When dealing with metadatas, remember to use `{self.metadata_column}.attribute` instead of `attribute` alone. The default name for it is `metadata`. Returns: List[Document]: List of Documents )similarity_search_by_vectorrr)rZr*r1rros rsimilarity_searchStarRocks.similarity_searchs5&//  # # / / 6 HN  rc URXU5n[URU5nUVs/sHSn[XpRR S[ R"XpRR S5S9PMU sn$s snf![a:n[RS[U5S[U5S35 /sSnA$SnAff=f)acPerform a similarity search with StarRocks by vectors Args: query (str): query string k (int, optional): Top K neighbors to retrieve. Defaults to 4. where_str (Optional[str], optional): where condition string. Defaults to None. NOTE: Please do not let end-user to fill this and always be aware of SQL injection. When dealing with metadatas, remember to use `{self.metadata_column}.attribute` instead of `attribute` alone. The default name for it is `metadata`. Returns: List[Document]: List of (Document, similarity) rOrQ page_contentrQrrrN) rr2r)rr}rRrloadsrrrrrF) rZrPr1rrorq_rr.rs rr%StarRocks.similarity_search_by_vectors.%%iI> "4??E:C   A !";;#9#9*#E!F!ZZ++*@*@*L(MN    LL?47)3CCF87S TI s/BAB B B C/CCCc URURRU5X#5n[URU5Vs/sHXn[ X`R RS[R"X`R RS5S9US4PMZ sn$s snf![a:n[RS[U5S[U5S35 /sSnA$SnAff=f) aKPerform a similarity search with StarRocks Args: query (str): query string k (int, optional): Top K neighbors to retrieve. Defaults to 4. where_str (Optional[str], optional): where condition string. Defaults to None. NOTE: Please do not let end-user to fill this and always be aware of SQL injection. When dealing with metadatas, remember to use `{self.metadata_column}.attribute` instead of `attribute` alone. The default name for it is `metadata`. Returns: List[Document]: List of documents rOrQrdistrrrN)rrrr2r)rr}rRrrrrrrrF)rZr*r1rrorr.rs r'similarity_search_with_relevance_scores1StarRocks.similarity_search_with_relevance_scoress&%%  # # / / 6  *$//5A BA %&{{'='=j'I%J!%Akk.D.DZ.P,Q!RfI B     LL?47)3CCF87S TI s0B+AB&#B+&B++ C/5/C*$C/*C/c[URSURRSURR35 g)z Helper function: Drop data zDROP TABLE IF EXISTS rsN)r2r)r}rTrVrs rdropStarRocks.drops9  OO#DKK$8$8#94;;;L;L:M N rc4URRS$)NrQ)r}rRrs rmetadata_columnStarRocks.metadata_columns{{%%j11rc URXS5n[URU5n[UVs/sHoSPM snUVs/sH2n[R "XR RS5PM4 snUVs/sHoUR RSPM snUVs/sH2n[R "XR RS5PM4 snUVs/sHoSPM snS9n [[R"U[RS9U SUUS 9n [U 5n [U 5V Vs/sHupX;dM UPM n n nU $s snfs snfs snfs snfs snfs snn f) NrNrPrOrQr)r6r7r9r:r;)dtyper7)r1 lambda_mult)rr2r)r4rrr}rRrnparrayfloat32_results_to_docsr&)rZrPr1fetch_krrorrr.results mmr_selected candidatesrselected_resultss r'max_marginal_relevance_search_by_vector1StarRocks.max_marginal_relevance_search_by_vectors^%%i$?t6"%&#Q4#&LOLOq 1[[33K@ABCGJJc// ;r?rfr|rpropertyr7rrr classmethodrrrrrrrrr rrA __classcell__)rs@rriris "/3B7B7,B7 B7  B7B7HW''49+/'+ 77(7 7 % 7  7 7r 59.2,02  ,  *  86IM (+8E 6BF    1> QT  4#' ## #! #  #  #LBF## #1>#QT# %#J 22              F +/37        )  1     rricL[U5VVs/sHupUPM snn$s snnfrX)_results_to_docs_and_scores)r docrs rrr5s#9'B CBFCCB CC Cs c[USUSUS5Vs/sH!n[USUS=(d 0S9US4PM# sn$s snf)Nr9r:r;rrrr)rr)r r,s rr(r(9sf K K K    F vay6!9? CVAYO   s'A)rrFrrrebool)rrrer)r)rr*rFrezList[dict[str, Any]])r rrer8)r rrer)0 __future__rrlogginghashlibr threadingrtypingrrrr r r r r numpyrlangchain_core.documentsrlangchain_core.embeddingsrlangchain_core.vectorstoresrpydantic_settingsrrtyping_extensionsr&langchain_community.vectorstores.utilsr getLoggerrrrr r2rFrHr!r+Metadatar4rCrirr(rrrr:s" MMM-03>'M       2 3c3t344 5%)%3 3lh h V Dr