dh]~SSKrSSKJrJrJrJrJrJr SSKr SSK J r SSK J r SSKJr SSKJr Sr"SS \5rg) N)AnyDictIterableListOptionalTuple)Document) Embeddings) VectorStore)maximal_marginal_relevancec~\rSrSrSrS\S\SS4SjrS*Sjr\ S\ \4S j5r S+S \ \ S \ \\S\S\\ 4S jjrS+S \ \ S \ \\S\S\\ 4S jjrS+S\ \\ S\S\ \4SjjrS+S\ \\ S\S\ \4Sjjr\4SS.S\\S\S\ \\ \ 4S\S\\\\\44 Sjjjr\4SS.S\ S\S\ \\ \ 4S\S\\\\44 Sjjjr\4SS.S\ S\S\ \\ \ 4S\S\\\\44 Sjjjr\4SS.S\ S\S\ \\ \ 4S\S\\\\44 Sjjjr\4SS.S\ S\S\ \\ \ 4S\S\\\\44 Sjjjr\4SS.S\\S\S\ \\ \ 4S\S\\4 Sjjjr \4SS.S\\S\S\ \\ \ 4S\S\\4 Sjjjr!\4SS.S\ S\S\ \\ \ 4S\S\\4 Sjjjr"\4SS.S\ S\S\ \\ \ 4S\S\\4 Sjjjr#\SS 4SS.S\\S\S!\S"\S\ \\ \ 4S\S\\4S#jjjr$\SS 4SS.S\\S\S!\S"\S\ \\ \ 4S\S\\4S$jjjr%S,SS.S\ S\S!\S"\S\ \\ \ 4S\S\\4S%jjjr&\SS 4SS.S\ S\S!\S"\S\ \\ \ 4S\S\\4S&jjjr'\(S+S \\ S\S \ \\S\SS4 S'jj5r)\(S+S \\ S\S \ \\S\SS4 S(jj5r*S)r+g)-SurrealDBStorea SurrealDB as Vector Store. To use, you should have the ``surrealdb`` python package installed. Args: embedding_function: Embedding function to use. dburl: SurrealDB connection url ns: surrealdb namespace for the vector store. (default: "langchain") db: surrealdb database for the vector store. (default: "database") collection: surrealdb collection for the vector store. (default: "documents") (optional) db_user and db_pass: surrealdb credentials Example: .. code-block:: python from langchain_community.vectorstores.surrealdb import SurrealDBStore from langchain_community.embeddings import HuggingFaceEmbeddings model_name = "sentence-transformers/all-mpnet-base-v2" embedding_function = HuggingFaceEmbeddings(model_name=model_name) dburl = "ws://localhost:8000/rpc" ns = "langchain" db = "docstore" collection = "documents" db_user = "root" db_pass = "root" sdb = SurrealDBStore.from_texts( texts=texts, embedding=embedding_function, dburl, ns, db, collection, db_user=db_user, db_pass=db_pass) embedding_functionkwargsreturnNc SSKJn URSS5UlURSSS:XaU"UR5UlO [ S5eURS S 5UlURS S 5UlURS S5Ul Xl X l g![an[S5UeSnAff=f)Nr)SurrealzZCannot import from surrealdb. please install with `pip install surrealdb`.dburlzws://localhost:8000/rpcwsz6Only websocket connections are supported at this time.ns langchaindbdatabase collection documents) surrealdbr ImportErrorpoprsdb ValueErrorrrrrr)selfrrres b/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/surrealdb.py__init__SurrealDBStore.__init__5s   )ZZ)BC ::a?d "tzz*DHUV V**T;/**T:. **\;?"4 # @  sB'' C1 B==Cc# URR5IShvN SUR;akSUR;a[URRS5nURRS5nURR XS.5IShvN URR UR UR5IShvN gNN?N 7f)zZ Initialize connection to surrealdb database and authenticate if credentials are provided Ndb_userdb_pass)userpass)r"connectrgetsigninuserr)r$r,passwords r& initializeSurrealDBStore.initializeOs hh    # T[[(@;;??9-D{{y1H((//4"BC C Chhll477DGG,,, ! D,s4CCA:CC7CCCCCc\[UR[5(a UR$S$N) isinstancerr )r$s r& embeddingsSurrealDBStore.embeddings[s1$11:>>  # #  texts metadatasc\# URR[U55n/n[U5HpupgXtUS.nUbU[ U5:aX&US'O/US'UR R URU5IShvN n URU SS5 Mr U$N!7f)zAdd list of text along with embeddings to the vector store asynchronously Args: texts (Iterable[str]): collection of text to add to the database Returns: List of ids for the newly inserted documents )text embeddingNmetadatarid) rembed_documentslist enumeratelenr"createrappend) r$r;r<rr8idsidxr>datarecords r& aadd_textsSurrealDBStore.aadd_textscs,,<Z #%Z 88??F JJvay '* sBB,B* "B,c ^SS[[S[[[S[ S[[4U4Sjjjn[ R"U"X40UD65$)zAdd list of text along with embeddings to the vector store Args: texts (Iterable[str]): collection of text to add to the database Returns: List of ids for the newly inserted documents r;r<rrcz># TR5IShvN TR"X40UD6IShvN $NN7fr6r3rL)r;r<rr$s r& _add_texts,SurrealDBStore.add_texts.._add_textss7 //# # #DVDD D $Ds;7;9;;r6)rstrrrdictrasynciorun)r$r;r<rrQs` r& add_textsSurrealDBStore.add_textssh"/3 EC= ET + E E#Y  E E{{:eA&ABBr:rHc# Uc.URRUR5IShvN g[U[5(a$URRU5IShvN g[U[ 5(aA[ U5S:a2UVs/sH%o0RRU5IShvN PM' nnggNN^Ns snf7f)zDelete by document ID asynchronously. Args: ids: List of ids to delete. **kwargs: Other keyword arguments that subclasses might use. Returns: Optional[bool]: True if deletion is successful, False otherwise. NTrF)r"deleterr7rSrCrE)r$rHrrA_s r&adeleteSurrealDBStore.adeletes ;((//$//2 2 2#s##hhooc***c4((SX\=@ASrxxr222SAA 3+3AsE,CC8C'C(-C"C 7C 8C CCC  Cc ^S[[[S[S[[4U4Sjjn[ R "U"U40UD65$)zDelete by document ID. Args: ids: List of ids to delete. **kwargs: Other keyword arguments that subclasses might use. Returns: Optional[bool]: True if deletion is successful, False otherwise. rHrrc|># TR5IShvN TR"SSU0UD6IShvN $N N7f)NrH)r3r\)rHrr$s r&_delete&SurrealDBStore.delete.._deletes8//# # #8#888 8 $8s<8<:<<)rrrSrboolrUrV)r$rHrras` r&rZSurrealDBStore.deletesE  9xS 2 9c 9htn 9{{731&122r:)filterr?krec T# URUUURSS5S.nSnU(a>UH8n[X75[[4;a SX7S3nOX7nUSUSUS3- nM: S US S US 3n UR R X5IS hvN n [U 5S:Xa/$U Sn U SS:wa SSKJ n U RSS5n U "U 5eU SVs/sH8n[USSUS0URS5=(d 0ES9USUS4PM: sn$Ns snf7f)aSRun similarity search for query embedding asynchronously and return documents and scores Args: embedding (List[float]): Query embedding. k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar along with scores score_thresholdr)rr?rfrh'z and metadata.z =  u select id, text, metadata, embedding, vector::similarity::cosine(embedding, $embedding) as similarity from ⟨rub⟩ where vector::similarity::cosine(embedding, $embedding) >= $score_threshold z4 order by similarity desc LIMIT $k; NstatusOK)SurrealExceptionresultz Unknown Errorr>rAr@) page_contentr@ similarityr?) rr/typerSrcr"queryrE surrealdb.wsrnr )r$r?rfrerargs custom_filterkey filter_valuersresultsrornerrdocs r&(_asimilarity_search_by_vector_with_score7SurrealDBStore._asimilarity_search_by_vector_with_scores~(//"%zz*;Q?    $d 3%&v{m1#5L&,k]L=Sa!HH l#$% /   u33 w<1 I ( t # 5**X7C"3' 'h'  (!$V"CIM#''*2E2KML!K  (  4  s%BD(D!A D( >D#D(#D(rsc# URRU5nUR"XR4SU0UD6IShvN VVVs/sH upgnXg4PM snnn$Ns snnnf7f)a.Run similarity search asynchronously and return relevance scores Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar along with relevance scores reNr embed_queryr| r$rsrfrerquery_embeddingdocumentrqr[s r&(asimilarity_search_with_relevance_scores7SurrealDBStore.asimilarity_search_with_relevance_scores$11==eDCC#/59? (a "   4AAAAAAc ^^^^^S[[[[44UUUUU4Sjjn[R "U"55$)a-Run similarity search synchronously and return relevance scores Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar along with relevance scores rc># TR5IShvN TR"TT4ST0TD6IShvN $N"N7fNre)r3rrerfrrsr$sr&(_similarity_search_with_relevance_scoreshSurrealDBStore.similarity_search_with_relevance_scores.._similarity_search_with_relevance_scoresFsO//# # #FFq!'+1  $>:><>>rrr floatrUrV)r$rsrfrerrs````` r&'similarity_search_with_relevance_scores6SurrealDBStore.similarity_search_with_relevance_scores3s;&  (E/ "A   {{CEFFr:c# URRU5nUR"XR4SU0UD6IShvN VVVs/sH upgnXg4PM snnn$Ns snnnf7f)a6Run similarity search asynchronously and return distance scores Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar along with relevance distance scores reNrrs r&asimilarity_search_with_score,SurrealDBStore.asimilarity_search_with_scorePrrc ^^^^^S[[[[44UUUUU4Sjjn[R "U"55$)a5Run similarity search synchronously and return distance scores Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar along with relevance distance scores rc># TR5IShvN TR"TT4ST0TD6IShvN $N"N7fr)r3rrsr&_similarity_search_with_scoreRSurrealDBStore.similarity_search_with_score.._similarity_search_with_scoresM//# # #;;q!'+1  $rr)r$rsrfrerrs````` r&similarity_search_with_score+SurrealDBStore.similarity_search_with_scorels7& T%%:P5Q   {{8:;;r:c# UR"X4SU0UD6IShvN VVs/sH un nUPM snn$Ns snnf7f)a,Run similarity search on query embedding asynchronously Args: embedding (List[float]): Query embedding k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar to the query reN)r|)r$r?rfrerrr[s r&asimilarity_search_by_vector+SurrealDBStore.asimilarity_search_by_vectorsc()-(U(U)%+)/5)## #!Q #  # s>6>8>>c t^^^^^S[[4UUUUU4Sjjn[R"U"55$)aRun similarity search on query embedding Args: embedding (List[float]): Query embedding k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar to the query rc># TR5IShvN TR"TT4ST0TD6IShvN $N"N7fr)r3r)r?rerfrr$sr&_similarity_search_by_vectorPSurrealDBStore.similarity_search_by_vector.._similarity_search_by_vectorsM//# # #::1%+/5  $rrr rUrV)r$r?rfrerrs````` r&similarity_search_by_vector*SurrealDBStore.similarity_search_by_vectors-& DN   {{79::r:c~# URRU5nUR"XR4SU0UD6IShvN $N7f)a Run similarity search on query asynchronously Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar to the query reN)rrr)r$rsrfrerrs r&asimilarity_search!SurrealDBStore.asimilarity_searchsM$11==eD66  '- 17    s 4=;=c t^^^^^S[[4UUUUU4Sjjn[R"U"55$)zRun similarity search on query Args: query (str): Query k (int): Number of results to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar to the query rc># TR5IShvN TR"TT4ST0TD6IShvN $N"N7fr)r3rrsr&_similarity_search._similarity_searchs>//# # #00S&SFSS S $Srr)r$rsrfrerrs````` r&similarity_search SurrealDBStore.similarity_searchs0& T$x. T T{{-/00r:?fetch_k lambda_multc4# UR"X4SU0UD6IShvN nUVs/sHoSPM n nUVs/sHoSPM n n[[R"U[RS9U UUS9n U V s/sHoU PM sn $Nks snfs snfs sn f7f)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. reNr)dtype)rfr)r|r nparrayfloat32) r$r?rfrrrerrosubdocsr8 mmr_selectedis r&(amax_marginal_relevance_search_by_vector7SurrealDBStore.amax_marginal_relevance_search_by_vectors8DD  '- 17   #))&3A&))/0#"g 01 HHYbjj 1 #  "..AQ..! *0/s6BBB B B B3B7 BB Bc |^^^^^^^S[[4UUUUUUU4Sjjn[R"U"55$)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. rc># TR5IShvN TR"TTTT4ST0TD6IShvN $N$N7fr)r3r)r?rrerfrrr$sr&(_max_marginal_relevance_search_by_vectorhSurrealDBStore.max_marginal_relevance_search_by_vector.._max_marginal_relevance_search_by_vector6sQ//# # #FF1g{;AEK  $A<A>AAr)r$r?rfrrrerrs``````` r&'max_marginal_relevance_search_by_vector6SurrealDBStore.max_marginal_relevance_search_by_vectors-: X   {{CEFFr:c# URRU5nUR"XrX44SU0UD6IShvN nU$N7f)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. reN)rrr) r$rsrfrrrerr?rs r&amax_marginal_relevance_search-SurrealDBStore.amax_marginal_relevance_search>sS:++77> BB ' 7= AG    s5A>Ac |^^^^^^^S[[4UUUUUUU4Sjjn[R"U"55$)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. rc># TR5IShvN TR"TTTT4ST0TD6IShvN $N$N7fr)r3r)rrerfrrrsr$sr&_max_marginal_relevance_searchTSurrealDBStore.max_marginal_relevance_search.._max_marginal_relevance_search}sQ//# # #<<q';7=AG  $rr)r$rsrfrrrerrs``````` r&max_marginal_relevance_search,SurrealDBStore.max_marginal_relevance_searchas-8 d8n   {{9;<$(3 d3i 33 $ 32I ,0 I ;I  I c3h( I  I  eHeS() *I \ ,0     c3h(     eHeO$ % >G ,0 GG G c3h( G  G eHeO$ %G@ ,0     c3h(     eHeO$ % >< ,0 << < c3h( <  < eHeO$ %<< ,0  ;   c3h(     h 8; ,0 ;;; ; c3h( ;  ; h;< ,0     c3h(     h 41 ,0 11 1 c3h( 1  1 h18 ,/,0,/;,/ ,/ ,/  ,/c3h(,/,/ h,/b #G,0#G;#G #G #G  #Gc3h(#G#G h#GP !,0!! ! !  !c3h(!! h!L "=,0"="= "= "=  "=c3h("="= h"=H +/ CyDJ'     > +/ CyDJ'     r:r)rUtypingrrrrrrnumpyrlangchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr &langchain_community.vectorstores.utilsr rrr`r:r&rs0==-03M q [q r: