tjQddlmZddlZddlmZmZmZmZmZm Z m Z ddl m Z ddl ZddlmZddlmZddlmZddlmZdd lmZerdd lmZejeZd d d d ddZedddGddeZdS)) annotationsN) TYPE_CHECKINGAnyIterableListOptionalTupleUnion)uuid4) deprecated)Document) Embeddings) VectorStore)maximal_marginal_relevance)MutationResult localhost19530F)hostportuserpasswordsecurez0.2.0z1.0z"langchain_milvus.MilvusVectorStore)sinceremovalalternative_importc eZdZdZ diddd dddd ddd djd*Zedkd,Zdld.Z dmdnd3Z dodpd5Z dqd6Z drd7Z dqd8Z dqd9Z dsdtd:Z dudd<dvdFZ dwdxdMZ dwdydPZ dwdzdRZ dwd{dSZ d|d}dYZ d|d~d[Z ddd]Zeddeddddfdd<dd_ZddbZdddZ dddhZdS)Milvusa`Milvus` vector store. DO NOT USE. KEPT FOR BACKWARDS COMPATIBILITY. You need to install `pymilvus` and run Milvus. See the following documentation for how to run a Milvus instance: https://milvus.io/docs/install_standalone-docker.md If looking for a hosted Milvus, take a look at this documentation: https://zilliz.com/cloud and make use of the Zilliz vectorstore found in this project. IF USING L2/IP metric, IT IS HIGHLY SUGGESTED TO NORMALIZE YOUR DATA. Args: embedding_function (Embeddings): Function used to embed the text. collection_name (str): Which Milvus collection to use. Defaults to "LangChainCollection". collection_description (str): The description of the collection. Defaults to "". collection_properties (Optional[dict[str, any]]): The collection properties. Defaults to None. If set, will override collection existing properties. For example: {"collection.ttl.seconds": 60}. connection_args (Optional[dict[str, any]]): The connection args used for this class comes in the form of a dict. consistency_level (str): The consistency level to use for a collection. Defaults to "Session". index_params (Optional[dict]): Which index params to use. Defaults to HNSW/AUTOINDEX depending on service. search_params (Optional[dict]): Which search params to use. Defaults to default of index. drop_old (Optional[bool]): Whether to drop the current collection. Defaults to False. auto_id (bool): Whether to enable auto id for primary key. Defaults to False. If False, you needs to provide text ids (string less than 65535 bytes). If True, Milvus will generate unique integers as primary keys. primary_field (str): Name of the primary key field. Defaults to "pk". text_field (str): Name of the text field. Defaults to "text". vector_field (str): Name of the vector field. Defaults to "vector". metadata_field (str): Name of the metadata field. Defaults to None. When metadata_field is specified, the document's metadata will store as json. The connection args used for this class comes in the form of a dict, here are a few of the options: address (str): The actual address of Milvus instance. Example address: "localhost:19530" uri (str): The uri of Milvus instance. Example uri: "http://randomwebsite:19530", "tcp:foobarsite:19530", "https://ok.s3.south.com:19530". host (str): The host of Milvus instance. Default at "localhost", PyMilvus will fill in the default host if only port is provided. port (str/int): The port of Milvus instance. Default at 19530, PyMilvus will fill in the default port if only host is provided. user (str): Use which user to connect to Milvus instance. If user and password are provided, we will add related header in every RPC call. password (str): Required when user is provided. The password corresponding to the user. secure (bool): Default is false. If set to true, tls will be enabled. client_key_path (str): If use tls two-way authentication, need to write the client.key path. client_pem_path (str): If use tls two-way authentication, need to write the client.pem path. ca_pem_path (str): If use tls two-way authentication, need to write the ca.pem path. server_pem_path (str): If use tls one-way authentication, need to write the server.pem path. server_name (str): If use tls, need to write the common name. Example: .. code-block:: python from langchain_community.vectorstores import Milvus from langchain_community.embeddings import OpenAIEmbeddings embedding = OpenAIEmbeddings() # Connect to a milvus instance on localhost milvus_store = Milvus( embedding_function = Embeddings, collection_name = "LangChainCollection", drop_old = True, auto_id = True ) Raises: ValueError: If the pymilvus python package is not installed. LangChainCollectionrNSessionFpktextvector) primary_field text_field vector_fieldmetadata_fieldpartition_key_fieldpartition_namesreplica_numbertimeout num_shardsembedding_functionrcollection_namestrcollection_descriptioncollection_propertiesOptional[dict[str, Any]]connection_argsconsistency_level index_paramsOptional[dict] search_paramsdrop_oldOptional[bool]auto_idboolr%r&r'r( Optional[str]r)r*Optional[list]r+intr,Optional[float]r- Optional[int]c  ddlm}m}n#t$rtdwxYwdddiddddiddddiddddiddddiddddiddddiddddd ddd diddd diddiddd d dddd ddddiddddidd|_||_||_||_||_||_ ||_ ||_ | |_ | |_ | |_| |_||_||_g|_||_||_||_||_|t.}|||_d|_||j|jrB||j|j|_|j|j|j| r5t;|j|r |jd|_||||dS)z#Initialize the Milvus vector store.r CollectionutilityzXCould not import pymilvus python package. Please install it with `pip install pymilvus`.L2nprobe ) metric_typeparamsef)rGrKsearch_k) itopk_size search_widthmin_iterationsmax_iterations team_size)IVF_FLATIVF_SQ8IVF_PQHNSW RHNSW_FLATRHNSW_SQRHNSW_PQIVF_HNSWANNOYSCANN AUTOINDEX GPU_CAGRA GPU_IVF_FLAT GPU_IVF_PQNusingr*r+r,) pymilvusrDrE ImportErrordefault_search_paramsembedding_funcr/r1r2r6r8r5r;_primary_field _text_field _vector_field_metadata_field_partition_key_fieldfieldsr*r+r,r-DEFAULT_MILVUS_CONNECTION_create_connection_aliasaliascolhas_collectionset_properties isinstancedrop_init)selfr.r/r1r2r4r5r6r8r9r;r%r&r'r(r)r*r+r,r-rDrEs e/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_community/vectorstores/milvus.py__init__zMilvus.__init__|s0  4 4 4 4 4 4 4 4 4   A  )-2GG'+"~FF&*xnEE$(T2J??*.4*EE(,r CC(,r CC(,2R8P8PQQ%)j"5EFF%)j"5EFF)-<<#"%$%&'&'!"   -1XrNKK*.8R.II/& & "41.&<#%:"(*!2 ,%)-$7!!# ., $  "7O22?CC )-  ! !$"6dj ! I I D!z$jDH)5''(BCCC   48Z88  HMMOOODH +)      s %returnc|jSN)rh)rxs ry embeddingszMilvus.embeddingss ""dictcddlm}m}|dd}|dd}|dd}|dd}|dd}|%|#t |d zt |z} n||d r|d d } n}|d r|d d } nLtd |td |||} nd} t d||} nd} | | D]p} | | d} | d rKd| vrG| d| kr;d| vr7| d| kr+t d| d| dcSqtj} |jdd| i|t d| | S#|$r"}td| |d}~wwxYw)z+Create the connection to the Milvus server.r)MilvusException connectionsrNraddressurir:zhttps://r$zhttp://zInvalid Milvus URI: %sz/Missing standard address type for reuse attemptrzUsing previous connection: %srqz Created new connection using: %sz)Failed to create new connection using: %s)rerrgetr0 startswithsplitloggererror ValueErrordebuglist_connectionsget_connection_addrr hexconnect)rxr4rrrrrrr given_addresstmp_userconaddrrqes ryrpzMilvus._create_connection_aliass99999999.11&$??*9*=*=fd*K*K!0!4!4Y!E!E,00==""6400   0IIOc$ii7MM _~~j)) @ # * 5 5a 8  ** @ # ) 4 4Q 7  5s;;; !93???  #MM M LLJ K K K  HHH  $"3355 " ""66s1v>>F""d**iM994f11LL!@#a&IIIq6MMM   K  ? ?e ? ? ? ? LL;U C C CL    LLDe L L LG s0+HI!H>>Ir~ metadatasOptional[list[dict]]Nonec|||||||||||dS)Nrd)_create_collection_extract_fields _create_index_create_search_params_load)rxr~rr*r+r,s ryrwz Milvus._init&s  !  # #J : : :   ""$$$ +)      rlistc Nddlm}m}m}m}m}ddlm}t|d} g} |j *| ||j |j n|r|d D]\} } || } | |j ks | |jkr.td| t#d| d| |jkr'| || |jd| || | | ||j|jd|jr-| ||j|jd d n-| ||j|jd d d | ||j||d| || |j|j} |j*||j||j|j|j|_n#||j||j|j|_|j!|j |jdSdS#|$r(}td|j||d}~wwxYw)Nr)rDCollectionSchemaDataType FieldSchemar)infer_dtype_bydataz>>>  K((*:v N N N    <  MM 'DRV     MM '$#!%      K*,>,>z!},M,MSV W W W   "! 3 $ 9    *&:-!&*&<*# &:-!&*&<* )5''(BCCCCC65    LL;T=QST   G  s9A:I77J$<#JJ$cddlm}t|j|r5|jj}|jD]#}|j|j"dSdS)z,Grab the existing fields from the CollectionrrDN)rerDrurrrrnrr)rxrDrxs ryrzMilvus._extract_fieldssq'''''' dh + + +X_F] + + ""16**** + + + +rcddlm}t|j|r5|jjD](}|j|jkr|cS)dS)z0Return the vector index information if it existsrrN)rerDrurrindexes field_namerkto_dict)rxrDrs ry _get_indexzMilvus._get_indexsj'''''' dh + + 'X% ' '<4#55599;;&&&6trcddlm}m}t|j|r| |jdddddd |_ |j|j|j|j nB#|$r:dd id |_|j|j|j|j YnwxYwt d |j dS#|$r'}t d |j |d}~wwxYwdSdS)z Create a index on the collectionrrDrNrFrW@)MefConstruction)rI index_typerJ)r6rcr^z/Successfully created an index on collection: %sz+Failed to create an index on collection: %s)rerDrrurrrr6 create_indexrkrqrrr/r)rxrDrrs ryrzMilvus._create_indexs88888888 dh + +' 0A0A0I& $,'+&,()R"@"@))D% H))*%)%6"j*'   (,&1"$))D% H))*%)%6"j*  E( #    A4CW  G' ' 0I0Is;C ,A65C6|dd}|dd}|j||_||jd<dSdSdSdS)z6Generate search params based on the current index typerrN index_paramrrI)rerDrurrr8rrg)rxrDindexrrIs ryrzMilvus._create_search_paramss'''''' dh + + @0B0JOO%%E "' "6|"D #(#7 #F %)%? %K"4?"=111  @ @0J0J  rc ddlm}m}ddlm}|jp|}t |j|r]|K| |j |j |j kr#|j |||dSdSdSdS)z!Load the collection if available.rrC) LoadStateNrbrd)rerDrEpymilvus.client.typesrr,rurrr load_stater/rqNotLoadload)rxr*r+r,rDrErs ryrz Milvus._loads 10000000333333,)' tx , , !!-""4#7tz"JJ !! HMM /-        --!!ridstexts Iterable[str]Optional[List[dict]] batch_sizerOptional[List[str]]kwargsr List[str]c ddlm}m}t|}jsyt |ts Jdt t|t |ks Jdtd|Ds Jd j |} n#t$rfd|D} YnwxYwt | dkrt dgSt j|sE| |d }jr j|d <jr j|d <jr j|d <jdi|j|j| ijs |j<j4|D]0} jg| 1ny|w|D]t} | D]]\} } jrfdjDndjD} | | vr)| g| ^uj}t |}g}t j|sJt7d||D]t9|z|fdjD} jp|}jj|fd |i|}||jd#|$r#}t d||d }~wwxYw|S)aInsert text data into Milvus. Inserting data when the collection has not be made yet will result in creating a new Collection. The data of the first entity decides the schema of the new collection, the dim is extracted from the first embedding and the columns are decided by the first metadata dict. Metadata keys will need to be present for all inserted values. At the moment there is no None equivalent in Milvus. Args: texts (Iterable[str]): The texts to embed, it is assumed that they all fit in memory. metadatas (Optional[List[dict]]): Metadata dicts attached to each of the texts. Defaults to None. should be less than 65535 bytes. Required and work when auto_id is False. timeout (Optional[float]): Timeout for each batch insert. Defaults to None. batch_size (int, optional): Batch size to use for insertion. Defaults to 1000. ids (Optional[List[str]]): List of text ids. The length of each item Raises: MilvusException: Failure to add texts Returns: List[str]: The resulting keys for each inserted element. rrz7A list of valid ids are required when auto_id is False.z7Different lengths of texts and unique ids are provided.c3`K|])}t|dkV*dS)rN)rencode.0rs ry z#Milvus.add_texts..2s5>>Qs188::&0>>>>>>rz1Each id should be a string less than 65535 bytes.cDg|]}j|Sr)rh embed_queryrrrxs ry z$Milvus.add_texts..9s*LLL$-99!<<LLLrzNothing to insert, skipping.)r~rr*r+r,Nc*g|]}|jk |Sr)rirs ryrz$Milvus.add_texts..\s&PPP1qD.^s!9!9!9!!9!9!9rc8g|]}|v|Srr)rrendi insert_dicts ryrz$Milvus.add_texts..ns7*+a;>N>N Aqu%>N>N>Nrz0Failed to insert batch starting at entity: %s/%sr)!rerDrrr;rursetallrhembed_documentsNotImplementedErrorrrrrr*r+r,rwrjrkrirl setdefaultrrrnrangemininsertextend primary_keysr)rxrrr,rrrrDrr~drrkeysvectors total_countpks insert_listresrrrrs` @@@ry add_textszMilvus.add_textss J 98888888U | c4((  I  (s3xx==CJJ...I/..>>#>>>>>  C  > M,<'(| 1$(Ly! DJ    e   ( | 3/2K+ ,   + K K&&t';R@@GGJJJJ K$"JJA&'ggiiJJ U $|:PPPP PPPP!9!9T[!9!9!9 $;;'223;;BB5IIIJ$D$67'll $(J/////q+z22  Aa*nk22C/3{K ,1'%dhokMM7MfMM 3+,,,,"    F;    s*B88CC%8KL#LLrNquerykparamexprList[Document]c |jtdgS|jp|}|jd|||||d|}d|DS)anPerform a similarity search against the query string. Args: query (str): The text to search. k (int, optional): How many results to return. Defaults to 4. param (dict, optional): The search params for the index type. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (int, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[Document]: Document results for search. N!No existing collection to search.)rrrrr,cg|]\}}|Srrrdoc_s ryrz,Milvus.similarity_search..&&&Q&&&rr)rrrrr,similarity_search_with_score)rxrrrrr,rrs rysimilarity_searchzMilvus.similarity_search~sw0 8  LL< = = =I,)'/d/ 1Eg  IO  '&#&&&&r embedding List[float]c |jtdgS|jp|}|jd|||||d|}d|DS)aPerform a similarity search against the query string. Args: embedding (List[float]): The embedding vector to search. k (int, optional): How many results to return. Defaults to 4. param (dict, optional): The search params for the index type. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (int, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[Document]: Document results for search. Nrrrrrr,cg|]\}}|Srrrs ryrz6Milvus.similarity_search_by_vector..r rr)rrrrr,&similarity_search_with_score_by_vector)rxrrrrr,rrs rysimilarity_search_by_vectorz"Milvus.similarity_search_by_vectorsw0 8  LL< = = =I,)'9d9 1Eg  QW  '&#&&&&rList[Tuple[Document, float]]c |jtdgS|j|}|jp|}|jd|||||d|}|S)aJPerform a search on a query string and return results with score. For more information about the search parameters, take a look at the pymilvus documentation found here: https://milvus.io/api-reference/pymilvus/v2.2.6/Collection/search().md Args: query (str): The text being searched. k (int, optional): The amount of results to return. Defaults to 4. param (dict): The search params for the specified index. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (float, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[float], List[Tuple[Document, any, any]]: Nrrr)rrrrrhrr,r) rxrrrrr,rrrs ryr z#Milvus.similarity_search_with_scores8 8  LL< = = =I'33E:: ,)'9d9 1Eg  QW   rc  |jtdgS||j}|jdd}||j|jp|}|jjd|g|j|||||d|}g} |dD]C fd|D} | | } | j f} | | D| S)ahPerform a search on a query string and return results with score. For more information about the search parameters, take a look at the pymilvus documentation found here: https://milvus.io/api-reference/pymilvus/v2.2.6/Collection/search().md Args: embedding (List[float]): The embedding vector being searched. k (int, optional): The amount of results to return. Defaults to 4. param (dict): The search params for the specified index. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (float, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[Tuple[Document, float]]: Result doc and score. Nrdata anns_fieldrlimitr output_fieldsr,rcFi|]}|j|Srentityrrrresults ry zAMilvus.similarity_search_with_score_by_vector..+CCCAv}((++CCCrr) rrrrr8rnremoverkr,search_parse_documentscorer)rxrrrrr,rrrretrr pairr!s @ryrz-Milvus.similarity_search_with_score_by_vectors8 8  LL< = = =I =&E AAA T/000,)'dho  )'      !f  FCCCC]CCCD&&t,,C&D JJt     r?fetch_k lambda_multfloatc |jtdgS|j|} |jp|}|jd| ||||||d|S)aPerform a search and return results that are reordered by MMR. Args: query (str): The text being searched. k (int, optional): How many results to give. Defaults to 4. fetch_k (int, optional): Total results to select k from. Defaults to 20. 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 param (dict, optional): The search params for the specified index. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (float, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[Document]: Document results for search. Nr)rrr,r-rrr,r)rrrrrhrr,'max_marginal_relevance_search_by_vector) rxrrr,r-rrr,rrs rymax_marginal_relevance_searchz$Milvus.max_marginal_relevance_search$sB 8  LL< = = =I'33E:: ,)';t;  #      r list[float]c >jtdgS|j}jdd} | jjp|}jjd |gj|||| |d|} g} g} g} | dD]nfd| D} |}| || j | j oj jd| jjg|fdDfd | D}tt!j|||| }g}|D]%}|d krn| | |&|S) aPerform a search and return results that are reordered by MMR. Args: embedding (str): The embedding vector being searched. k (int, optional): How many results to give. Defaults to 4. fetch_k (int, optional): Total results to select k from. Defaults to 20. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5 param (dict, optional): The search params for the specified index. Defaults to None. expr (str, optional): Filtering expression. Defaults to None. timeout (float, optional): How long to wait before timeout error. Defaults to None. kwargs: Collection.search() keyword arguments. Returns: List[Document]: Document results for search. NrrrcFi|]}|j|Srrr s ryr"zBMilvus.max_marginal_relevance_search_by_vector..r#r in )rrr,cBi|]}|j|jSr)rirkrs ryr"zBMilvus.max_marginal_relevance_search_by_vector..s+RRRQ1T()1T-?+@RRRrc g|] }| Srr)rrrs ryrzBMilvus.max_marginal_relevance_search_by_vector..s$=$=$=AWQZ$=$=$=r)rr-r)rrrrr8rnr$rkr,r%r&rr'idrrirnparray)rxrrr,r-rrr,rrrr documentsscoresrr ordered_result_embeddings new_orderingr(rr!rs` @@ryr0z.Milvus.max_marginal_relevance_search_by_vectorVs@ 8  LL< = = =I =&E AAA T/000,)'dho  )'       !f " "FCCCC]CCCD&&t,,C   S ! ! ! MM&, ' ' ' JJvy ! ! ! !(..'22S22.0BC!   SRRR'RRR$=$=$=$=$=$=$=!2 HY  !:a[    ) )ABww 9Q<(((( rrc  t|trBoth ids and expr are provided. Ignore expr and delete by ids.r5z0Either ids list or expr string must be provided.rr) rurrrwarningrir0rrdelete)rxrrrs ryrBz Milvus.deletes c4 SXX\\T)44s44DDdC((  B  (tx33D3F333rdict[str, Any]c  t| trt| dkrd} nd} |d||||||| | d| } | ||| | S)aCreate a Milvus collection, indexes it with HNSW, and insert data. Args: texts (List[str]): Text data. embedding (Embeddings): Embedding function. metadatas (Optional[List[dict]]): Metadata for each text if it exists. Defaults to None. collection_name (str, optional): Collection name to use. Defaults to "LangChainCollection". connection_args (dict[str, Any], optional): Connection args to use. Defaults to DEFAULT_MILVUS_CONNECTION. consistency_level (str, optional): Which consistency level to use. Defaults to "Session". index_params (Optional[dict], optional): Which index_params to use. Defaults to None. search_params (Optional[dict], optional): Which search params to use. Defaults to None. drop_old (Optional[bool], optional): Whether to drop the collection with that name if it exists. Defaults to False. ids (Optional[List[str]]): List of text ids. Defaults to None. Returns: Milvus: Milvus Vector Store rFT)r.r/r4r5r6r8r9r;)rrrr)rurrr)clsrrrr/r4r5r6r8r9rrr; vector_dbs ry from_textszMilvus.from_textssP c4  SXX\\GGGC  (++/%'       %9#FFFrrr ct||j|jr||jn|S)N) page_contentmetadata)r poprjrl)rxrs ryr&zMilvus._parse_documentsK$"2337;7KUTXXd2333QU    rList[int] | Nonec ddlm}jtddS j|jg}n0#|$r(}tdj||d}~wwxYwfd|D}|S)zGet primary keys with expression Args: expr: Expression - E.g: "id in [1, 2]", or "title LIKE 'Abc%'" Returns: List[int]: List of IDs (Primary Keys) rrNz!No existing collection to get pk.)rrzFailed to get ids: %s error: %scDg|]}|jSr)rri)ritemrxs ryrz"Milvus.get_pks.. s(FFFtxx+,,FFFr) rerrrrrrrirr/)rxrrr query_resultexcrs` ryget_pkszMilvus.get_pks s -,,,,, 8  LL< = = =4 8>>$*=)>*LL    LL:Dr+r?r,r@r-rA)r{r)r4rr{r0)NNNr$N) r~r>rrr*r>r+r?r,r@r{rr})r~rrrr{r)r{r)r{r3)Nr$N)r*r>r+r?r,r@r{r)NNr)rrrrr,r@rr?rrrrr{r)rNNNN)rr0rr?rr7rr=r,r@rrr{r)rrrr?rr7rr=r,r@rrr{r)rr0rr?rr7rr=r,r@rrr{r)rrrr?rr7rr=r,r@rrr{r)rNr*r+NNN)rr0rr?r,r?r-r.rr7rr=r,r@rrr{r)rr2rr?r,r?r-r.rr7rr=r,r@rrr{r)NN)rrrr=rrr{r)rrrrrrr/r0r4rCr5r0r6r7r8r7r9r<rrrrr{r)rrr{r )rr0rrr{rL)rrr<rTrrr{rU)__name__ __module__ __qualname____doc__rzpropertyr~rprwrrrrrrrr rr rr1r0rB classmethodrorGr&rSrXrrryrrsu WWx 5&(:>48!*'+(,#(j " $(,-1*.#'$(+j j j j j j X###X#8888x&**.*.#'      (CGeeeeeN++++++++Z @ @ @ @+/#' 4+/#' y$(yyyyyy| $"#' '''''H $"#' '''''H $"#' &&&&&V $"#' :::::~ $"#'0 0 0 0 0 j $"#'XXXXXvFJ444440 +/4*C!*'+(,8$(88888[8t    8$(+/"""""""rr) __future__rloggingtypingrrrrrr r uuidr numpyr:langchain_core._api.deprecationr langchain_core.documentsr langchain_core.embeddingsrlangchain_core.vectorstoresr&langchain_community.vectorstores.utilsrpymilvus.orm.mutationr getLoggerrYrrorrrryrks""""""MMMMMMMMMMMMMMMMMM666666------000000333333MMMMMM5444444  8 $ $       ; ccccc[cc  cccr