dh,%SSKJr SSKrSSKrSSKrSSKrSSKJr SSKJ r J r J r J r J r JrJrJrJrJrJrJrJr SSKrSSKJr SSKJr SSKJr SSKJr SS K J!r! \ (aSSK"r"\S r#\$"\"\#55r%S \&S '\S r'\$"\"\'55r(S\&S'Sr)Sr*Sr+\+S-r,/SQr-/SQr.SS0/r/\R`"\15r2S/Sjr3S0Sjr4S1Sjr5S2S3Sjjr6\"SSSS9"SS \55r7S4S5S!jjr8S6S7S"jjr9S8S#jr:S$/S4S9S%jjr;S:S&jrS=S)jr?S>S*jr@S?S+jrAS@SAS,jjrBSBS-jrCSCS.jrDg)D) annotationsN)deepcopy) TYPE_CHECKINGAnyCallableDictIterableListLiteralOptionalSizedTupleTypeUnionget_args) deprecated)Document) Embeddings) VectorStore)maximal_marginal_relevance)L2IPzList[DISTANCE_METRICS]AVAILABLE_DISTANCE_METRICS) TileDBDense TileDBSparse FaissFlat FaissIVFFlatFlinngz List[ENGINES]AVAILABLE_ENGINES langchain ) _distanceidcontent)r$r&blobzMissing propertyc[U[5(a[[U[5(aF[U5[U5:wa.[USUSUS[U5SUS[U53 5eg)z Check that sizes of two variables are the same Args: x: Variable to compare y: Variable to compare x_name: Name for variable x y_name: Name for variable y z and z% expected to be equal length but len(z)=z and len(N) isinstancer len ValueError)xyx_namey_names ]/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/vdms.py_len_check_if_sizedr1?ss!U 1e 4 4Q3q69IheF8$("SVHIfXRAx A   cL[U5VVs/sHupUPM snn$s snnfN)_results_to_docs_and_scores)resultsdoc_s r0_results_to_docsr9Qs#9'B CBFCCB CC Cs c/nUSup#[U5S:aSUS;aSUSS;aUSSSnUHvn[USS5nUSn[H nX;dM XX M UR5V V s0sHupU [;dMX_M n n n UR [ X{S9U45 Mx U$s sn n f![a#n [RSU 35 Sn A U$Sn A ff=f) NrFindDescriptorentitiesr$ r&) page_contentmetadataz2No results returned. Error while parsing results: ) r*roundINVALID_DOC_METADATA_KEYSitemsINVALID_METADATA_VALUEappendr Exceptionloggerwarning) r6 final_res responsesblobsresult_entitiesentdistance txt_contentspmkeymvalpropses r0r5r5Us$IQ"1:  NQ  IaL0il+;<<'l+;#B><B8B8!B>8B>> C+C&&C+cSSKnUR"5nURX5 U$![a [S5ef=f)zyVDMS client for the VDMS server. Args: host: IP or hostname of VDMS server port: Port to connect to VDMS server rNzOCould not import vdms python package. Please install it with `pip install vdms.)vdms ImportErrorconnect)hostportrUclients r0 VDMS_Clientr[wsK YY[F NN4 M   8   s *Az0.3.18z1.0.0zlangchain_vdms.VDMS)sinceremovalalternative_importc\rSrSrSrS\SSSSS.S5Sjjr\S6Sj5rS7S jr S8S jr S9S jr S:S jr S;S jr \\S4SSjjrS?S@SjjrS=SASjjrSBSCSjjrSDSESjjr/S4SFSjjrSGSHSjjrSISjrSS\S4SJSjjrSKSLSjjrSS\4SMSjjrS\4SNSjjrSOSjrSPSjrSQS jr SRSSS!jjr!STSUS"jjr"\\SSSS4SVS#jjr#SWS$jr$\%SS\\4SXS%jj5r&\%SSS\\4SYS&jj5r'SSS/4SZS'jjr(\\S(S4S[S)jjr)\\S(S4S\S*jjr*\\S(S4S]S+jjr+\\S(S4S^S,jjr,SS\\SSS4S_S-jjr-\\S4S`S.jjr.\\S4SaS/jjr/\\S4SbS0jjr0\\S4ScS1jjr1SdS2jr2SeS3jr3S4r4g)fVDMSaIntel Lab's VDMS for vector-store workloads. To use, you should have both: - the ``vdms`` python package installed - a host (str) and port (int) associated with a deployed VDMS Server Visit https://github.com/IntelLabs/vdms/wiki more information. IT IS HIGHLY SUGGESTED TO NORMALIZE YOUR DATA. Args: client: VDMS Client used to connect to VDMS server collection_name: Name of data collection [Default: langchain] distance_strategy: Method used to calculate distances. VDMS supports "L2" (euclidean distance) or "IP" (inner product) [Default: L2] engine: Underlying implementation for indexing and computing distances. VDMS supports TileDBDense, TileDBSparse, FaissFlat, FaissIVFFlat, and Flinng [Default: FaissFlat] embedding: Any embedding function implementing `langchain_core.embeddings.Embeddings` interface. relevance_score_fn: Function for obtaining relevance score Example: .. code-block:: python from langchain_huggingface import HuggingFaceEmbeddings from langchain_community.vectorstores.vdms import VDMS, VDMS_Client model_name = "sentence-transformers/all-mpnet-base-v2" vectorstore = VDMS( client=VDMS_Client("localhost", 55555), embedding=HuggingFaceEmbeddings(model_name=model_name), collection_name="langchain-demo", distance_strategy="L2", engine="FaissFlat", ) Nrr) embeddingcollection_namedistance_strategyenginerelevance_score_fnembedding_dimensionscXlXPlX@lX lUR X75 X`lUR UURURS9Ulg)Nremetric)_clientsimilarity_search_enginerdrb_check_required_inputsoverride_relevance_score_fnadd_set_collection_name)selfrZrbrcrdrerfrgs r0__init__ VDMS.__init__s] (.%!2" ##OJ,>(!% 00))!-! r2cUR$r4)rbrqs r0 embeddingsVDMS.embeddingss ~~r2c[UR[5(aURRU5$SnUS- n[ U5e)Nz*Must provide `embedding` which is expectedz to be an Embeddings object)r)rbrembed_documentsr+)rqtextsp_strs r0_embed_documentsVDMS._embed_documentssC dnnj 1 1>>11%8 8@E 2 2EU# #r2c URb9[URS5(aURR"SSU0UD6$[S5e)N embed_videopathsz:Must provide `embedding` which has attribute `embed_video`)rbhasattrrr+)rqrkwargss r0 _embed_videoVDMS._embed_videosI >> %'$..-*P*P>>--DEDVD DL r2cURb4[URS5(aURRUS9$[S5e)N embed_imageurisz:Must provide `embedding` which has attribute `embed_image`)rbrrr+)rqrs r0 _embed_imageVDMS._embed_imagesD >> %'$..-*P*P>>--4-8 8L r2c[UR[5(aURRU5$[ S5e)NzEMust provide `embedding` which is expected to be an Embeddings object)r)rbr embed_queryr+)rqtexts r0 _embed_queryVDMS._embed_querys8 dnnj 1 1>>--d3 3W r2cURb UR$URR5S;aS$[SURS35e)a The 'correct' relevance function may differ depending on a few things, including: - the distance / similarity metric used by the VectorStore - the scale of your embeddings (OpenAI's are unit normed. Many others are not!) - embedding dimensionality - etc. )ipl2cU$r4r)r,s r01VDMS._select_relevance_score_fn..sQr2z=No supported normalization function for distance_strategy of z;.Consider providing relevance_score_fn to VDMS constructor.)rnrdlowerr+rus r0_select_relevance_score_fnVDMS._select_relevance_score_fnsf  + + 733 3  ! ! ' ' )\ 9 --1-C-C,DEMM r2c URcSUS'UR"SUUUUS.UD6n/nUHHupURcURX45 M&URUURU 545 MJ U$)z?Return docs and their similarity scores on a scale from 0 to 1.Tnormalize_distance)querykfetch_kfilterr)rnsimilarity_search_with_scorerD) rqrrrrrdocs_and_scoresdocs_and_rel_scoresr7scores r0(_similarity_search_with_relevance_scores-VDMS._similarity_search_with_relevance_scores s  + + 3+/F' (;;     *,)JC//7#**C<8#**88? *#"r2c [X#SS5 UbUOUVs/sHnSPM snn[X$SS5 UbUO-UVs/sH!n[[R"55PM# snn[X%SS5 /n/n/n [ XCX%5HQuppUR XXU S9upUcMUR U5 UR U5 U R U 5 MS URXx5unnU $s snfs snf)Nrzrv metadatasidsr?rbdocumentr%)r1struuiduuid4zip_VDMS__get_add_queryrD_VDMS__run_vdms_query)rqrcrzrvrrr8 all_queries all_blobs inserted_idsmetaembr7r%rr'responseresponse_arrays r0addVDMS.add*s Ew E!*!6I5?d{"  LL " : %') A222**11!4    y)    G!sDFc[XUS9nURU/5upV[U5S:a[US5R S5nU$[ [ 5nU$)N) unique_entitydeletionr,)_find_property_entityrr* _bytes2strsplitrDEFAULT_PROPERTIES)rqrcrr find_queryr response_blobrs r0__get_propertiesVDMS.__get_propertiessn + 8 #'"7"7 "E }  !$.}Q/?$@$F$Fs$K !%$%--?$@ !$$r2cURRX5upE[X5nU(aURR5 XE4$r4)rkr_check_valid_responseprint_last_response)rqrrrrrr8s r0__run_vdms_queryVDMS.__run_vdms_querysA $(<<#5#5k#M  !+ 8  LL , , .''r2c "[X#SS5 [X$SS5 UbUOUVs/sHnSPM snn[X%SS5 URU5n/n[XTX25HuppSUR0n SSS /0nU bSU /US '[ S USSSSSUU S 9 nUR U/5unnUR UU U U U S 9unnUcMeUR U/U/5unnURU 5 M URXUR5 gs snf)zs Updates (find, delete, add) a collection based on id. If more than one collection returned with id, error occuers r documentsrvNrrrrrr%r;rr) r1rrrrrrrD_VDMS__update_properties)rqrcrrrvrr8 orig_props updated_idsrrr7r%r6rrrrr's r0__update VDMS.__updatesZ CE;?CULA!*!6I32-I(=#!)#@)% #33KL ! J 1r2Tc UVs/sHopRUS9PM nnU(a#U(a[U5H upXrU S'M O%U(a/nUHnURSU05 M UbUO-UV s/sH!n [[R "55PM# sn nUR US9n UcUV s/sHn 0PM nn OUV s/sHn [U 5PM nn UR"SUU UUUS.UD6 U$s snfs sn fs sn fs sn f)aARun more images through the embeddings and add to the vectorstore. Images are added as embeddings (AddDescriptor) instead of separate entity (AddImage) within VDMS to leverage similarity search capability Args: uris: List of paths to the images to add to the vectorstore. metadatas: Optional list of metadatas associated with the images. ids: Optional list of unique IDs. batch_size (int): Number of concurrent requests to send to the server. add_path: Bool to add image path as metadata Returns: List of ids from adding images into the vectorstore. ) image_pathr rrzrvrr batch_sizer) encode_image enumeraterDrrrr_validate_vdms_propertiesadd_from) rqrrrr add_pathruri b64_textsmidxr8rvms r0 add_imagesVDMS.add_images1s#2CGG$3&&#&6$ G  &t_ 03$ -- I  ,!45_cd*Kd3tzz|+XX%%2!) F    '#:(    ! !:/I/I r2cURR5(d [S5eUR[;a [S5eUR [ ;a [S5eURc [S5eUbX lOURb;[URS5(a [URS55UlOURb[URS5(d[URS5(aW[URS 5(a1URRRRUlO [S 5eURU5n[US 5(aUR R#U5 gX0lg![a [S 5ef=f) Nz_VDMS client must be connected to a VDMS server.Please use VDMS_Client to establish a connectionz-distance_strategy must be either 'L2' or 'IP'z]engine must be either 'TileDBDense', 'TileDBSparse', 'FaissFlat', 'FaissIVFFlat', or 'Flinng'Must provide embedding functionrzThis is a sample sentence.rrmodelz>Embedding dimension needed. Please define embedding_dimensionsr)rk is_connectedr+rdrrlrrbrrr*rr-token_embedding embedding_dimrrr")rqrcrg current_propss r0rmVDMS._check_required_inputss||((**E   ! !)C CLM M  ( (0A A=  >> !>? ?  +'; $ ^^ 'GDNNM,R,R'*!!">?(D $^^ ' DNNM 2 2t~~}55t~~w//,,<<JJ,!T --o> 40 1 1  & & - -m <4A &"$Xs 2/F22Gc /n/nSS/S.n[SUSSSSSSUS9 nURU5 URX#5upgUSSS$)Nrr%)countrr;rrreturned)rrDr)rqrcrrr6rrrs r0r4 VDMS.count'su!# ! /     5!#'#8#8#P {+,Z88r2c.[R"U5$r4)base64 b64decode)rq base64_images r0 decode_imageVDMS.decode_image=s --r2c DUbUO URnURXQUS9$)zDelete by ID. These are the IDs in the vectorstore. Args: ids: List of ids to delete. Returns: Optional[bool]: True if deletion is successful, False otherwise, None if not implemented. )rr)rp _VDMS__delete)rqrrcrrnames r0delete VDMS.delete@s) #2"=4CXCX}}T }DDr2cSnSn[UUUUS9nURU/U5upU(aXyS;aU SUSSSnXU4$)Nrr;)rr6rr<rr$)rr) rqsetnamerr6r normalizemax_dist command_strrrrs r0get_k_candidatesVDMS.get_k_candidatesSsq&      $(#8#8%)#L   3{;/ ;B? LH11r2c /n [U5n U bU RU 5 UcURX#XiUS9upn GOK MPN K(4W=kJ!P ''I#s2 Gc[US5nUR5n[R"U5R S5sSSS5 $!,(df  g=f)Nrbzutf-8)openreadr8 b64encodedecode)rqr fr's r0r VDMS.encode_images> *d #q668D##D)009$ # #s 5A  Ac USnURUUVs/sHoRPM snUVs/sHoRPM snUUUUS9$s snfs snf)aCreate a VDMS vectorstore from a list of documents. Args: collection_name (str): Name of the collection to create. documents (List[Document]): List of documents to add to vectorstore. embedding (Embeddings): Embedding function. Defaults to None. ids (Optional[List[str]]): List of document IDs. Defaults to None. batch_size (int): Number of concurrent requests to send to the server. Returns: VDMS: VDMS vectorstore. rZ)rZrzrrbrr rc) from_textsr>r?) clsrrbrr rcrrZr7s r0from_documentsVDMS.from_documentssc,#8,~~/89y##y9/89y||y9!+  99s A A c USnU"UUUS9n Uc-UV s/sH!n [[R"55PM# nn U RUUUUS9 U $s sn f)aCreate a VDMS vectorstore from a raw documents. Args: texts (List[str]): List of texts to add to the collection. embedding (Embeddings): Embedding function. Defaults to None. metadatas (Optional[List[dict]]): List of metadatas. Defaults to None. ids (Optional[List[str]]): List of document IDs. Defaults to None. batch_size (int): Number of concurrent requests to send to the server. collection_name (str): Name of the collection to create. Returns: VDMS: VDMS vectorstore. rZ)rcrbrZ)rzrrr )rrrr) r]rzrbrrr rcrrZvdms_collectionr8s r0r\VDMS.from_textsss0#8,+  ;.34e3tzz|$eC4!!! " 5s'Ac/n/nSS0nUbX7S'SU;aURU5nXS'SU;aSUS '[S USUUS 9n URU 5 URXV5upX4$) a6Gets the collection. Get embeddings and their associated data from the data store. If no constraints provided returns all embeddings up to limit. Args: constraints: A dict used to filter results by. E.g. `{"color" : ["==", "red"], "price": [">", 4.00]}`. Optional. limit: The number of documents to return. Optional. include: A list of what to include in the results. Can contain `"embeddings"`, `"metadatas"`, `"documents"`. Ids are always included. Defaults to `["metadatas", "documents"]`. Optional. r4rNlimitr?rrvTr'r;)rrr6)rrrDr) rqrcrrdincluderrr6rrrrs r0getVDMS.gets("$ ! #*B-  $G   $($9$9/$J !3FO 7 ""GFO  #   5!#'#8#8#P ''r2g?c URc [S5e[RR U5(d-[ URS5(aUR U5nO[RR U5(a/[ URS5(aURU/S9SnOn[RR U5(a/[ URS5(aURU/S9SnOSUS 3nUS - nUS - n[U5eURUUUUUS 9n U $ aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: query (str): Query to look up. Text or path for image or video. 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.rrrrrr(Could not generate embedding for query ''.9If using path for image or video, verify embedding model 6has callable functions 'embed_image' or 'embed_video'.) lambda_multr) rbr+osrisfilerrrr'max_marginal_relevance_search_by_vector) rqrrrrorrembedding_vector error_msgdocss r0max_marginal_relevance_search"VDMS.max_marginal_relevance_search9s*4 >> !T  ww~~e$$)O)O#007  WW^^E " "wt~~}'M'M#00ug0>qA  WW^^E " "wt~~}'M'M#00w0?B B5'LI T TI Q QIY' ';;  # <  r2c URU/UU/SQS9n[USS5S:Xa/$USSVs/sHn[[U55PM n n[ [ R "U[ RS9U UUS9n [U5n [U 5V V s/sHupX;dM U PM nn n U$s snfs sn n faReturn 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. )rr distancesrv)query_embeddings n_resultsrrerrdtype)rro) query_collection_embeddingsr*r_bytes2embeddingrrKarrayfloat32r9r )rqrbrrrorrr6r)embedding_list mmr_selected candidatesirselected_resultss r0rr,VDMS.max_marginal_relevance_search_by_vectoros422'[I 3  wqz!}  "I>EQZ]=J6%f-.] 6"**5' L*'2J( 3 3daq7H3  $ #! sB5 B:*B:c URc [S5e[RR U5(d-[ URS5(aUR U5nO[RR U5(a/[ URS5(aURU/S9SnOn[RR U5(a/[ URS5(aURU/S9SnOSUS 3nUS - nUS - n[U5eURUUUUUS 9n U $ri) rbr+rprrqrrrr2max_marginal_relevance_search_with_score_by_vector) rqrrrrorrrbrtrus r0(max_marginal_relevance_search_with_score-VDMS.max_marginal_relevance_search_with_scores(4 >> !T ww~~e$$)O)O))%0I WW^^E " "wt~~}'M'M))w)7:I WW^^E " "wt~~}'M'M)))8;IB5'LI T TI Q QIY' 'FF  # G  r2c URU/UU/SQS9n[USS5S:Xa/$USSVs/sHn[[U55PM n n[ [ R "U[ RS9U UUS9n [U5n [U 5V V Vs/sHun upX;dMX4PM nn n nU$s snfs snn n fry) rr*rrrrKrrr5r )rqrbrrrorrr6r)rrrrrsrs r0r7VDMS.max_marginal_relevance_search_with_score_by_vectors422'[I 3  wqz!}  "I>EQZ]=J6%f-.] 6"**5' L5W=J)2*(= (=91fqAR(=  $ #! sB; C.Cc /n Uc URnUcU $URSS/5n UcSU ;aURSU ;S.nUH-n URSUUUUUUU S9upU R X/5 M/ U $)Nrerrv)rr'r;)rrrr6rrM)rprfrrQrD)rqr{rcr|rrr6rr all_responsesreqembrrs r0r VDMS.query_collection_embeddingss$&  ""33O  # **Y 6 ?{g522$/G %D'+'C'C %"#5 $(D ( $H  (!; <%r2c fUR"U4X#US.UD6nUVVs/sHupxUPM snn$s snnf)aRun similarity search with VDMS. Args: query (str): Query to look up. Text or path for image or video. k (int): Number of results to return. Defaults to 3. fetch_k (int): Number of candidates to fetch for knn (>= k). filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of documents most similar to the query text. )rrr)r) rqrrrrrrr7r8s r0similarity_searchVDMS.similarity_search:sE&;;   :@ #22//222s -c HUR"SU/UUUS.UD6n[U5$)aReturn docs most similar to embedding vector. Args: embedding (List[float]): Embedding to look up documents similar to. k (int): Number of Documents to return. Defaults to 3. fetch_k (int): Number of candidates to fetch for knn (>= k). filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List of Documents most similar to the query vector. r{r|rrr)rr9rqrbrrrrr6s r0similarity_search_by_vector VDMS.similarity_search_by_vectorRs>"22 '[     ((r2c URc [S5e[RR U5(d-[ URS5(aUR U5nO[RR U5(a/[ URS5(aURU/S9SnOn[RR U5(a/[ URS5(aURU/S9SnOSUS 3nUS - nUS - n[U5eUR"S U/UUUS .UD6n[U5$)aRun similarity search with VDMS with distance. Args: query (str): Query to look up. Text or path for image or video. k (int): Number of results to return. Defaults to 3. fetch_k (int): Number of candidates to fetch for knn (>= k). filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Tuple[Document, float]]: List of documents most similar to the query text and cosine distance in float for each. Lower score represents more similarity. r,rrrrrrjrkrlrmrnrr) rbr+rprrqrrrrrr5) rqrrrrrrMrtr6s r0r!VDMS.similarity_search_with_scorems1* >> !>? ?77>>%((WT^^]-S-S/3/@/@/G&&74>>=+Q+Q"&"3"3%"3"A!"D&&74>>=+Q+Q"&"3"35'"3"B1"EFugRP XX UU  ++66"1!2   G+733r2c HUR"SU/UUUS.UD6n[U5$)a Return docs most similar to embedding vector and similarity score. Args: embedding (List[float]): Embedding to look up documents similar to. k (int): Number of Documents to return. Defaults to 3. fetch_k (int): Number of candidates to fetch for knn (>= k). filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Tuple[Document, float]]: List of documents most similar to the query text. Lower score represents more similarity. rr)rr5rs r0&similarity_search_with_score_by_vector+VDMS.similarity_search_with_score_by_vectors>022 '[    +733r2c*URX/U/5$)zUpdate a document in the collection. Args: document_id (str): ID of the document to update. document (Document): Document to update. )update_documents)rqrc document_idrs r0update_documentVDMS.update_documents$$_mhZPPr2cUVs/sHoDRPM nnUVs/sHn[UR5PM nnURU5nUR UUUUUS9 gs snfs snf)zUpdate a document in the collection. Args: ids (List[str]): List of ids of the document to update. documents (List[Document]): List of documents to update. )rrvrN)r>rr?r| _VDMS__update)rqrcrrrrr?rvs r0rVDMS.update_documentss7@@i(%%i@IR IRX %h&7&7 8  **40   !  A s A$A))rkrprrdrbrrnrl)rZ vdms.vdmsrbOptional[Embeddings]rcrrdDISTANCE_METRICSreENGINESrfz"Optional[Callable[[float], float]]rg Optional[int]returnNone)rr)rz List[str]rList[List[float]])rrrrrr)rrrr)rrr List[float])rzCallable[[float], float]) rrrintrrrOptional[Dict[str, Any]]rrrList[Tuple[Document, float]])NN) rcrrzrrvrr1Optional[Union[List[None], List[Dict[str, Any]]]]rOptional[List[str]]rr )rr)rcrrerrjrrr)rcrrzUnion[None, List[str]]rUnion[None, Dict[str, Any]]rbool)NNNN) rcrr? Optional[Any]rbUnion[List[float], None]rrr% Optional[str]rz4Tuple[Dict[str, Dict[str, Any]], Union[bytes, None]]FF)rcrrOptional[bool]rrrr)rz List[Dict]rOptional[List]rrrTuple[Any, Any]r4) rcrrrrrrvrrrrr)rcrrr rrrr)rrrOptional[List[dict]]rrr rrrrrrr)NNNrT)rrrzrrrrrr rrrrrrr) rzz Iterable[str]rrrrr rrrrr)rzrrvrrrrrr rrrrr)rcrrgzUnion[int, None]rr)rcrrr)r:rrbytes)NNN) rrrcrrOptional[Dict]rrrr)NNF) rCrrrr6rrrrDrrz(Tuple[List[Dict[str, Any]], List, float])rFrrCrrrrrrOptional[dict]r6rrMzOptional[List[float]]rrrz!Tuple[List[Dict[str, Any]], List])r rrr)r] Type[VDMS]rList[Document]rbrrrr rrcrrrrr`)r]rrzrrbrrrrrr rrcrrrrr`) rcrrrrdrrerrr)rrrrrrrofloatrOptional[Dict[str, List]]rrrr)rbrrrrrrorrrrrrr)rrrrrrrorrrrrrr)rbrrrrrrorrrrrrr)r{zOptional[List[List[float]]]rcrr|rrrrrr6rrrrrrz!List[Tuple[Dict[str, Any], List]]) rrrrrrrrrrrr) rbrrrrrrrrrrr) rrrrrrrrrrrr) rbrrrrrrrrrrr)rcrrrrrrr)rcrrrrrrr)5__name__ __module__ __qualname____firstlineno____doc__DEFAULT_COLLECTION_NAMErrpropertyrvr|rrrr DEFAULT_KDEFAULT_FETCH_Krrror>rrrrrDEFAULT_INSERT_BATCH_SIZErrrrrmr4r;r@rGrQr  classmethodr^r\rfrvrrrrrrrrrrr__static_attributes__rr2r0r`r`s $T+/6.2%AE.2  (    ,   ? ,   8$4&+/ ## # # ) #  # &#JHL#' &  E  !  H&#' !  0'+37 +/+/$+/1 +/  +/`#'.2"& 6 6  6 , 6  6  6  >6 v).#( %%&%! %  %&%'.3 ( (" (, (  (&HL 9 9 9  9 & 9 E 9  9 vMM(,M$2 M  M.+/#'3#' 66(6! 6  6 ! 66 6v&**.#'#'66#6( 6 ! 6  6!66 6v+/#'3 ''('! '  '  ' '\+/3 ##&# # ( #  ## #J6B"6B:J6B 6Bp9,. $()-&* E E'E$ E  E  E.-1$($) 222* 2 " 2 " 2 226%&&*,015#(J(J(J( J(  J( $ J(*J(/J(!J( +J(X: +/#'36    !  (  !             D+/*.#'36& &&(&( & ! &  &&& &&V'+#(\ 0(0($0( 0(  0(  0(j& ,0 44 4 4  4 * 44 4r& ,0 5$5$ 5$ 5$  5$ * 5$5$ 5$t& ,0 22 2 2  2 * 22 &2n& ,0 5$5$ 5$ 5$  5$ * 5$5$ &5$r9=)-"&.2/3#('5''' '  ' , '-'!'' +'X&,0 33 3 3 * 3  3 36&,0 )) ) ) * )  ) )<&,0 ,4,4 ,4 ,4 * ,4  ,4 &,4b&,0 44 4 4 * 4  4 &4B Q" Q14 Q@H Q  Q " )2 ?M  r2r`c SU0n SU;a U(aX)S'UbX9S'U[;aXIS'SU;aUbXYS'SU;aUb[U5U S'SU;aU[;aXyS 'SU;aU[;aXS 'X 0n U $) NsetAddr_ref propertiesrFindrrr6)rCr) rFrCrrrRrrrr6entityrs r0rrs$W-F w v **$|  0v !8 #K 0} 4J!J +} 0F!F#y  !E Lr2c US:XaF[SX455(a.UUS.n UbX;S'UbXKS'UbX[S'US04;aXkS'UbX{S'O7US :Xa#S U0n U(aXS 'U S04;aXS 'U bXS 'O[SU35eX 0n U $)Nrc3&# UHoSLv M g7fr4r).0vars r0 %_add_descriptorset..s1#3C4#3s)r? dimensionsrerjrrrrrrrr6zUnknown command: )allr+) rFr?num_dimsrerjrrRrrrr6rrs r0rrs((S1$(#31..""   %8   %8  ? 6N r "#(<  !6N + + #-< tRj ($/= !   '9 ,[M:;;  !E Lr2c[U5S:aSRU5OSnSn0nSUS'SUS'S U0nS US 'X%S 'XTS'[U5n0nXGU'Xv4$) Nrrr AddEntityrclassTr'r?zqueryable propertiestyper&)r*join _str2bytes)rcrall_properties_str querytyperrR byte_datars r0_add_entity_with_blobr?s695H15L.1RTIF"F7OF6N#_5E*E&M)) <-.IE)  r2findc>/n/n/SQnUR5U;a)[SRSRU555eUR5S:Xa[ USS9nUR U5 XE4$UR5S:Xa2[ X5upxUR U5 UR U5 XE4$UR5S:XaJ[ USS 9nUR U5 [ X5upxUR U5 UR U5 XE4$) N)rrrz"[!] Invalid type. Choices are : {}rrT)rrr)r)rr+formatrrrDr) rcrrrrrchoicesrrs r0rrUs  KH'G7*=DDSXXgEVWXXv%%oTJ5!"        &0Q5! "        )%oE5!1Q5! "   r2c0[R"USS9nU$)Nrr})rK frombuffer)r'rs r0rrxs --I .C Jr2c"UR5$r4)rX)in_bytess r0rr}s ?? r2c [[UVVs/sHoR5Ho"PM M snn55$s snnfr4)rrr)rqrs r0_get_cmds_from_queryrs0  > 1VVXQXQ >? @@>s <cv^[U5n[T[5=(a [U4SjU55nU$)Nc3># UH4nUTS;=(a STSU;=(a TSUSS:v M6 g7f)rr5Nr)rcmdrs r0r(_check_valid_response..s[3C x{ - (1+c* * - QK Z (1 , -s;>)rr)rany)rrcmd_list valid_ress ` r0rrs<#K0H8T*s3 30I r2cvSSU/0n[SUUS/SS.S9nU/nURU5upg[XV5nX4$)Nr%rr;r)rr4rJ)rrr) rZrCr%rfindDescriptorrresr8rs r0rrs\ $$K$"- N ""K \\+ &FC%k7I  $$r2cZSnUb%[R"USS9nUR5nU$)zConvert embedding to bytes.Nrr})rKrtobytes)rbr'rs r0rrs/ Dhhy 2{{} Kr2cSn0nSUS'U(aXS'0nSUS'SUS'S /US 'XTS '0nU(aS S /US'S U/US'XdS'0nXGU'U$)N FindEntityrruniqueTr'rr4r&rr6rrrr?rr)rcrrrrr6rrs r0rrs IF"F7O(x GGFOGG kGFO9"$K$(!9 K 1K'=E) Lr2c,[RU5$r4)rencode)in_strs r0rrs ::f r2c0nUR5H)up#[U[5(aMX1[U5'M+ U$r4)rBr)rr)r? new_metadatakeyrs r0rrs;#%Lnn& %&&%*S "' r2) r,rr-rr.rr/rrr)r6rrr)r6rrr) localhosti)rXrrYrrr)NNNNNNN)rFrrCrrrrrrRrrrrrrrr6rrDict[str, Dict[str, Any]]) NNNNNNFNN)rFrr?rrrrerrjrrrrRrrrrrrrr6rrDict[str, Any])rcrrr rzTuple[Dict[str, Any], bytes]) rcrrrrr rrrr)r'rrr)rrrr)rrrr)rz List[dict]rrrr)rZrrCrr%rrzTuple[bool, Any])rbrrzUnion[bytes, None]r)rcrrrrrrr)r rrr)r?rrr)E __future__rr8loggingrprcopyrtypingrrrrr r r r r rrrrnumpyrKlangchain_core._api.deprecationrlangchain_core.documentsrlangchain_core.embeddingsrlangchain_core.vectorstoresr&langchain_community.vectorstores.utilsrrUrrr__annotations__rrrrrrrrArC getLoggerrrFr1r9r5r[r`rrrrrrrrrrrrrrr2r0rs "   6-03M 6:(CS:T5U2U  $((9#:=:% a-3<,dB7   8 $ $DD( (G@UVP ;P WP r*  !%"&"## # #  #  #  ## ###R#   "&"44 44  4  4  4 4 44 444n*.!0 ! ! ! !  !  !F A% % % % %&%*$! 8r2