
    dh                        S SK Jr  S SKrS SKrS SKJrJrJrJrJ	r	J
r
JrJr  S SKrS SKJr  S SKJr  S SKJr  S SKJr  S SKJr  \(       a  S S	KJrJr  S S
KJr  \R<                  " \5      r  " S S\5      r!g)    )annotationsN)TYPE_CHECKINGAnyIterableListOptionalTupleUnioncast)Document)
Embeddings)batch_iterate)VectorStore)maximal_marginal_relevance
AsyncIndexIndex)
InfoResultc                     \ rS rSrSr      S$SS.             S%S jjjr\S&S j5       r    S'S jrS(S	 jr	   S)SS.             S*S
 jjjr
   S)SS.             S+S jjjr    S,SS.               S-S jjjr    S,SS.               S-S jjjr  S.SS.           S/S jjjr  S.SS.           S/S jjjrS0S jr  S.SS.           S1S jjjr  S.SS.           S1S jjjr  S.SS.           S2S jjjr  S.SS.           S2S jjjr  S.SS.           S3S jjjr  S.SS.           S3S jjjr  S.SS.           S/S jjjr  S.SS.           S/S jjjr    S4SS.               S5S jjjr    S4SS.               S5S jjjr    S4SS.               S6S jjjr    S4SS.               S6S jjjr\         S7SS.                           S8S jjj5       r\         S7SS.                           S8S jjj5       r   S9SS.           S:S jjjr    S9SS.           S:S  jjjr!S;S! jr"S;S" jr#S#r$g)<UpstashVectorStore   a  Upstash Vector vector store

To use, the ``upstash-vector`` python package must be installed.

Also an Upstash Vector index is required. First create a new Upstash Vector index
and copy the `index_url` and `index_token` variables. Then either pass
them through the constructor or set the environment
variables `UPSTASH_VECTOR_REST_URL` and `UPSTASH_VECTOR_REST_TOKEN`.

Example:
    .. code-block:: python

        from langchain_openai import OpenAIEmbeddings
        from langchain_community.vectorstores import UpstashVectorStore

        embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
        vectorstore = UpstashVectorStore(
            embedding=embeddings,
            index_url="...",
            index_token="..."
        )

        # or

        import os

        os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
        os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."

        vectorstore = UpstashVectorStore(
            embedding=embeddings
        )
N 	namespacec                   SSK JnJn	  U(       aB  [	        X)5      (       d  [        S[        U5       35      eX l        [        R                  S5        U(       aB  [	        X85      (       d  [        S[        U5       35      eX0l
        [        R                  S5        U(       a3  U(       a,  U	" XES9U l        U" XES9U l
        [        R                  S	5        OOU(       dH  U(       dA  U	R                  " 5       U l        UR                  " 5       U l
        [        R                  S
5        X`l        Xl        Xpl        g! [         a    [        S5      ef = f)a  
Constructor for UpstashVectorStore.

If index or index_url and index_token are not provided, the constructor will
attempt to create an index using the environment variables
`UPSTASH_VECTOR_REST_URL`and `UPSTASH_VECTOR_REST_TOKEN`.

Args:
    text_key: Key to store the text in metadata.
    index: UpstashVector Index object.
    async_index: UpstashVector AsyncIndex object, provide only if async
    functions are needed
    index_url: URL of the UpstashVector index.
    index_token: Token of the UpstashVector index.
    embedding: Embeddings object or a boolean. When false, no embedding
        is applied. If true, Upstash embeddings are used. When Upstash
        embeddings are used, text is sent directly to Upstash and
        embedding is applied there instead of embedding in Langchain.
    namespace: Namespace to use from the index.

Example:
    .. code-block:: python

        from langchain_community.vectorstores.upstash import UpstashVectorStore
        from langchain_community.embeddings.openai import OpenAIEmbeddings

        embeddings = OpenAIEmbeddings()
        vectorstore = UpstashVectorStore(
            embedding=embeddings,
            index_url="...",
            index_token="...",
            namespace="..."
        )

        # With an existing index
        from upstash_vector import Index

        index = Index(url="...", token="...")
        vectorstore = UpstashVectorStore(
            embedding=embeddings,
            index=index,
            namespace="..."
        )
r   r   zdCould not import upstash_vector python package. Please install it with `pip install upstash_vector`.zGPassed index object should be an instance of upstash_vector.Index, got z#Using the index passed as parameterzLPassed index object should be an instance of upstash_vector.AsyncIndex, got z)Using the async index passed as parameter)urltokenz;Created index from the index_url and index_token parametersz)Created index using environment variablesN)upstash_vectorr   r   ImportError
isinstance
ValueErrortype_indexloggerinfo_async_indexfrom_env_embeddings	_text_key
_namespace)
selftext_keyindexasync_index	index_urlindex_token	embeddingr   r   r   s
             `/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/upstash.py__init__UpstashVectorStore.__init__;   s%   p	8 e++ ;-) 
  KKK=>k66 ,-/ 
 !,KKCDIADK *y LDKKUV{..*DK * 3 3 5DKKCD$!#I  	G 	s   D8 8Ec                    U R                   $ )z/Access the query embedding object if available.)r(   r+   s    r2   
embeddingsUpstashVectorStore.embeddings   s         c                    U R                   (       d  [        S5      e[        U R                   [        5      (       a$  U R                   R	                  [        U5      5      $ [        U5      $ )z)Embed strings using the embeddings objectLNo embeddings object provided. Pass an embeddings object to the constructor.)r(   r!   r    r   embed_documentslist)r+   textss     r2   _embed_documents#UpstashVectorStore._embed_documents   s\     @  d&&
33##33DK@@ E{r9   c                    U R                   (       d  [        S5      e[        U R                   [        5      (       a  U R                   R	                  U5      $ U$ )z-Embed query text using the embeddings object.r;   )r(   r!   r    r   embed_query)r+   texts     r2   _embed_queryUpstashVectorStore._embed_query   sQ    @  d&&
33##//55 r9   c          	         U Vs/ sH  owR                   PM     nnU Vs/ sH  owR                  PM     n	nU R                  " U4U	UUUUS.UD6$ s  snf s  snf )q  
Get the embeddings for the documents and add them to the vectorstore.

Documents are sent to the embeddings object
in batches of size `embedding_chunk_size`.
The embeddings are then upserted into the vectorstore
in batches of size `batch_size`.

Args:
    documents: Iterable of Documents to add to the vectorstore.
    batch_size: Batch size to use when upserting the embeddings.
    Upstash supports at max 1000 vectors per request.
    embedding_batch_size: Chunk size to use when embedding the texts.
    namespace: Namespace to use from the index.

Returns:
    List of ids from adding the texts into the vectorstore.

)	metadatas
batch_sizeidsembedding_chunk_sizer   )page_contentmetadata	add_texts
r+   	documentsrJ   rI   rK   r   kwargsdocr>   rH   s
             r2   add_documents UpstashVectorStore.add_documents   sl    : .77Yc!!Y7-67Yc\\Y	7~~
!!5
 
 	
 87s
   AAc          	        #    U Vs/ sH  owR                   PM     nnU Vs/ sH  owR                  PM     n	nU R                  " U4U	UUUUS.UD6I Sh  vN $ s  snf s  snf  N7f)rG   rH   rJ   rI   rK   r   N)rL   rM   
aadd_textsrO   s
             r2   aadd_documents!UpstashVectorStore.aadd_documents   sy     : .77Yc!!Y7-67Yc\\Y	7__
!!5
 
 
 	
 87
s%   A$AA$AA$A"A$c          
        Uc  U R                   n[        U5      nU=(       d.    U Vs/ sH!  n[        [        R                  " 5       5      PM#     snnU(       a  U V	s/ sH  oR                  5       PM     nn	OU Vs/ sH  n0 PM     nn[        X!5       H  u  pXU R                  '   M     [        S[        U5      U5       Hq  nXX-    nX<X-    nX,X-    nU R                  U5      n[        U[        UUU5      5       H0  nU R                  R                  " SU[        [        U5      S.UD6  M2     Ms     U$ s  snf s  sn	f s  snf )  
Get the embeddings for the texts and add them to the vectorstore.

Texts are sent to the embeddings object
in batches of size `embedding_chunk_size`.
The embeddings are then upserted into the vectorstore
in batches of size `batch_size`.

Args:
    texts: Iterable of strings to add to the vectorstore.
    metadatas: Optional list of metadatas associated with the texts.
    ids: Optional list of ids to associate with the texts.
    batch_size: Batch size to use when upserting the embeddings.
    Upstash supports at max 1000 vectors per request.
    embedding_batch_size: Chunk size to use when embedding the texts.
    namespace: Namespace to use from the index.

Returns:
    List of ids from adding the texts into the vectorstore.

r   vectorsr    )r*   r=   struuiduuid4copyzipr)   rangelenr?   r   r#   upsertr   r+   r>   rH   rJ   rI   rK   r   rQ   _mrM   rC   ichunk_texts	chunk_idschunk_metadatasr7   batchs                     r2   rN   UpstashVectorStore.add_texts  sB   @ IU77Ac$**,'7 +459a9I5I%*+UUI+ ")3NH'+T^^$ 4 q#e*&:;AA$<=K 89I'A,DEO..{;J&C	:G "" !T#y-AEK < 
3 8 6+s   'D8D=<Ec          
       #    Uc  U R                   n[        U5      nU=(       d.    U Vs/ sH!  n[        [        R                  " 5       5      PM#     snnU(       a  U V	s/ sH  oR                  5       PM     nn	OU Vs/ sH  n0 PM     nn[        X!5       H  u  pXU R                  '   M     [        S[        U5      U5       Hy  nXX-    nX<X-    nX,X-    nU R                  U5      n[        U[        UUU5      5       H8  nU R                  R                  " SU[        [        U5      S.UD6I Sh  vN   M:     M{     U$ s  snf s  sn	f s  snf  N7f)r[   Nr   r\   r^   )r*   r=   r_   r`   ra   rb   rc   r)   rd   re   r?   r   r&   rf   r   rg   s                     r2   rW   UpstashVectorStore.aadd_textsQ  sV    @ IU77Ac$**,'7 +459a9I5I%*+UUI+ ")3NH'+T^^$ 4 q#e*&:;AA$<=K 89I'A,DEO..{;J&C	:G ''.. !T#y-AEK   < 
3 8 6+s5   (E'EEE7E>E	B*E3E4Ec               L    U R                   " U R                  U5      4X#US.UD6$ )p  Retrieve texts most similar to query and
convert the result to `Document` objects.

Args:
    query: Text to look up documents similar to.
    k: Number of Documents to return. Defaults to 4.
    filter: Optional metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents most similar to the query and score for each
kfilterr   )&similarity_search_by_vector_with_scorerD   r+   queryru   rv   r   rQ   s         r2   similarity_search_with_score/UpstashVectorStore.similarity_search_with_score  s7    * ::e$
()I
QW
 	
r9   c               h   #    U R                   " U R                  U5      4X#US.UD6I Sh  vN $  N7f)rs   rt   N)'asimilarity_search_by_vector_with_scorerD   rx   s         r2   asimilarity_search_with_score0UpstashVectorStore.asimilarity_search_with_score  sD     * AAe$
()I
QW
 
 	
 
s   )202c                ,   / nU H  nUR                   nU(       aR  U R                  U;   aB  UR                  U R                  5      n[        XTS9nUR	                  XcR
                  45        Mh  [        R                  SU R                   S35        M     U$ )NrL   rM   zFound document with no `z` key. Skipping.)rM   r)   popr   appendscorer$   warning)r+   resultsdocsresrM   rC   rR   s          r2   _process_results#UpstashVectorStore._process_results  s|    C||HDNNh6||DNN3DDS)),-.t~~.>>NO  r9   c          	        U=(       d    SnUc  U R                   n[        U[        5      (       a#  U R                  R                  " SUUSUUS.UD6nO"U R                  R                  " SUUSUUS.UD6nU R                  U5      $ )>Return texts whose embedding is closest to the given embeddingr   Tdatatop_kinclude_metadatarv   r   vectorr   r   rv   r   r^   )r*   r    r_   r#   ry   r   r+   r1   ru   rv   r   rQ   r   s          r2   rw   9UpstashVectorStore.similarity_search_by_vector_with_score  s     2Ii%%kk'' !%# G kk''  !%# G $$W--r9   c          	     <  #    U=(       d    SnUc  U R                   n[        U[        5      (       a+  U R                  R                  " SUUSUUS.UD6I Sh  vN nO*U R                  R                  " SUUSUUS.UD6I Sh  vN nU R                  U5      $  N@ N7f)r   r   NTr   r   r^   )r*   r    r_   r&   ry   r   r   s          r2   r}   :UpstashVectorStore.asimilarity_search_by_vector_with_score  s      2Ii%% --33 !%#  G !--33  !%#  G $$W--%s$   ABB*BBBBc               f    U R                   " U4X#US.UD6nU VVs/ sH  u  pxUPM	     snn$ s  snnf )aE  Return documents most similar to query.

Args:
    query: Text to look up documents similar to.
    k: Number of Documents to return. Defaults to 4.
    filter: Optional metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents most similar to the query and score for each
rt   rz   	r+   ry   ru   rv   r   rQ   docs_and_scoresrR   rh   s	            r2   similarity_search$UpstashVectorStore.similarity_search  sE    ( ;;

>D
 #22//222   -c                  #    U R                   " U4X#US.UD6I Sh  vN nU VVs/ sH  u  pxUPM	     snn$  Ns  snnf 7f)a2  Return documents most similar to query.

Args:
    query: Text to look up documents similar to.
    k: Number of Documents to return. Defaults to 4.
    filter: Optional metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents most similar to the query
rt   Nr~   r   s	            r2   asimilarity_search%UpstashVectorStore.asimilarity_search3  sT     ( !% B B!
!
>D!
 
 #22//22
 3   ?7	?9??c               f    U R                   " U4X#US.UD6nU VVs/ sH  u  pxUPM	     snn$ s  snnf )D  Return documents closest to the given embedding.

Args:
    embedding: Embedding to look up documents similar to.
    k: Number of Documents to return. Defaults to 4.
    filter: Optional metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents most similar to the query
rt   )rw   	r+   r1   ru   rv   r   rQ   r   rR   rh   s	            r2   similarity_search_by_vector.UpstashVectorStore.similarity_search_by_vectorL  sE    ( EE
Y
BH
 #22//222r   c                  #    U R                   " U4X#US.UD6I Sh  vN nU VVs/ sH  u  pxUPM	     snn$  Ns  snnf 7f)r   rt   N)r}   r   s	            r2   asimilarity_search_by_vector/UpstashVectorStore.asimilarity_search_by_vectore  sT     ( !% L L!
Y!
BH!
 
 #22//22
 3r   c               .    U R                   " U4X#US.UD6$ )P
Since Upstash always returns relevance scores, default implementation is used.
rt   r   rx   s         r2   (_similarity_search_with_relevance_scores;UpstashVectorStore._similarity_search_with_relevance_scores~  s,     00

>D
 	
r9   c               J   #    U R                   " U4X#US.UD6I Sh  vN $  N7f)r   rt   Nr   rx   s         r2   )_asimilarity_search_with_relevance_scores<UpstashVectorStore._asimilarity_search_with_relevance_scores  s9      77

>D
 
 	
 
s   #!#c          
        Uc  U R                   n[        U R                  [        5      (       d   e[        U[        5      (       a-  U R
                  R                  " SUUSSU=(       d    SUS.UD6nO,U R
                  R                  " SUUSSU=(       d    SUS.UD6n[        [        R                  " U/[        R                  S9U V	s/ sH  oR                  PM     sn	UUS9n
U
 Vs/ sH  oU   R                  PM     nnU Vs/ sH&  n[        UR                  U R                  5      US9PM(     sn$ s  sn	f s  snf s  snf )	  Return 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 metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents selected by maximal marginal relevance.
Tr   r   r   include_vectorsr   rv   r   r   r   r   r   rv   r   dtyperu   lambda_multr   r^   )r*   r    r7   r   r_   r#   ry   r   nparrayfloat32r   rM   r   r   r)   r+   r1   ru   fetch_kr   rv   r   rQ   r   itemmmr_selectedrj   selectedrM   s                 r2   'max_marginal_relevance_search_by_vector:UpstashVectorStore.max_marginal_relevance_search_by_vector  sH   < I$//:6666i%%kk''  $!%|# G kk''   $!%|# G 2HHi[

3%,-WT[[W-#	
 2>>AAJ''> %
$ (,,"@8T$
 	
 . ?
s   D6
*D;,E c          
       #    Uc  U R                   n[        U R                  [        5      (       d   e[        U[        5      (       a5  U R
                  R                  " S	UUSSU=(       d    SUS.UD6I Sh  vN nO4U R
                  R                  " S	UUSSU=(       d    SUS.UD6I Sh  vN n[        [        R                  " U/[        R                  S9U V	s/ sH  oR                  PM     sn	UUS9n
U
 Vs/ sH  oU   R                  PM     nnU Vs/ sH&  n[        UR                  U R                  5      US9PM(     sn$  N Ns  sn	f s  snf s  snf 7f)
r   NTr   r   r   r   r   r   r^   )r*   r    r7   r   r_   r&   ry   r   r   r   r   r   rM   r   r   r)   r   s                 r2   (amax_marginal_relevance_search_by_vector;UpstashVectorStore.amax_marginal_relevance_search_by_vector  sc    > I$//:6666i%% --33  $!%|#  G !--33   $!%|#  G 2HHi[

3%,-WT[[W-#	
 2>>AAJ''> %
$ (,,"@8T$
 	
7 . ?
sN   A5E7E84E,E
-0EE
1E<EE,EE
EEc          
     V    U R                  U5      nU R                  " SUUUUUUS.UD6$ )  Return 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 metadata filter in str format
    namespace: Namespace to use from the index.

Returns:
    List of Documents selected by maximal marginal relevance.
r1   ru   r   r   rv   r   r^   )rD   r   	r+   ry   ru   r   r   rv   r   rQ   r1   s	            r2   max_marginal_relevance_search0UpstashVectorStore.max_marginal_relevance_search%  sH    < %%e,	;; 
#
 
 	
r9   c          
     r   #    U R                  U5      nU R                  " SUUUUUUS.UD6I Sh  vN $  N7f)r   r   Nr^   )rD   r   r   s	            r2   amax_marginal_relevance_search1UpstashVectorStore.amax_marginal_relevance_searchN  sU     < %%e,	BB 
#
 
 
 	
 
s   .757c               N    U " SUUUU	U
UUS.UD6nUR                  UUUUUUS9  U$ )  Create a new UpstashVectorStore from a list of texts.

Example:
    .. code-block:: python
        from langchain_community.vectorstores.upstash import UpstashVectorStore
        from langchain_community.embeddings import OpenAIEmbeddings

        embeddings = OpenAIEmbeddings()
        vector_store = UpstashVectorStore.from_texts(
            texts,
            embeddings,
        )
)r1   r,   r-   r.   r/   r0   r   rV   r^   )rN   clsr>   r1   rH   rJ   rK   rI   r,   r-   r.   r/   r0   r   rQ   vector_stores                  r2   
from_textsUpstashVectorStore.from_textsw  sa    >  	
##	
 	
 	!!5 	 	
 r9   c               j   #    U " SUUUU	UU
US.UD6nUR                  UUUUUUS9I Sh  vN   U$  N7f)r   )r1   r,   r-   r.   r   r/   r0   )rH   rJ   rI   r   rK   Nr^   )rW   r   s                  r2   afrom_textsUpstashVectorStore.afrom_texts  ss     >  	
##	
 	
 %%!!5 & 
 	
 	
 	
s   (313c                   Uc  U R                   nU(       a  U R                  R                  US9  gUb,  [        X15       H  nU R                  R	                  XdS9  M     g[        S5      ea  Delete by vector IDs

Args:
    ids: List of ids to delete.
    delete_all: Delete all vectors in the index.
    batch_size: Batch size to use when deleting the embeddings.
    namespace: Namespace to use from the index.
    Upstash supports at max 1000 deletions per request.
Nr   )rJ   r   z+Either ids or delete_all should be provided)r*   r#   resetr   deleter!   r+   rJ   
delete_allrI   r   rQ   rn   s          r2   r   UpstashVectorStore.delete  sn    $ IKK	2  _&z7""u"B 8
  JKKr9   c                 #    Uc  U R                   nU(       a"  U R                  R                  US9I Sh  vN   gUb4  [        X15       H$  nU R                  R	                  XdS9I Sh  vN   M&     g[        S5      e NG N7fr   )r*   r&   r   r   r   r!   r   s          r2   adeleteUpstashVectorStore.adelete  s     $ I##))I)>>>  _&z7''..5.NNN 8
  JKK ? Os!   3BA=2B(A?)B?Bc                6    U R                   R                  5       $ )   Get statistics about the index.

Returns:
    - total number of vectors
    - total number of vectors waiting to be indexed
    - total size of the index on disk in bytes
    - dimension count for the index
    - similarity function selected for the index
)r#   r%   r6   s    r2   r%   UpstashVectorStore.info  s     {{!!r9   c                R   #    U R                   R                  5       I Sh  vN $  N7f)r   N)r&   r%   r6   s    r2   ainfoUpstashVectorStore.ainfo)  s"      &&++----s   '%')r&   r(   r#   r*   r)   )rC   NNNNN)r,   r_   r-   Optional[Index]r.   Optional[AsyncIndex]r/   Optional[str]r0   r   r1   !Optional[Union[Embeddings, bool]]r   r_   )returnr   )r>   Iterable[str]r   z#Union[List[List[float]], List[str]])rC   r_   r   Union[List[float], str])N      )rP   List[Document]rJ   Optional[List[str]]rI   intrK   r   r   r   rQ   r   r   	List[str])rP   zIterable[Document]rJ   r   rI   r   rK   r   r   r   rQ   r   r   r   )NNr   r   )r>   r   rH   Optional[List[dict]]rJ   r   rI   r   rK   r   r   r   rQ   r   r   r   )   N)ry   r_   ru   r   rv   r   r   r   rQ   r   r   List[Tuple[Document, float]])r   r   r   r   )r1   r   ru   r   rv   r   r   r   rQ   r   r   r   )ry   r_   ru   r   rv   r   r   r   rQ   r   r   r   )r1   r   ru   r   rv   r   r   r   rQ   r   r   r   )r      g      ?N)r1   r   ru   r   r   r   r   floatrv   r   r   r   rQ   r   r   r   )ry   r_   ru   r   r   r   r   r   rv   r   r   r   rQ   r   r   r   )	NNr   r   rC   NNNN)r>   r   r1   r   rH   r   rJ   r   rK   r   rI   r   r,   r_   r-   r   r.   r   r/   r   r0   r   r   r_   rQ   r   r   r   )NNr   )rJ   r   r   zOptional[bool]rI   zOptional[int]r   r   rQ   r   r   None)r   r   )%__name__
__module____qualname____firstlineno____doc__r3   propertyr7   r?   rD   rS   rX   rN   rW   rz   r~   r   rw   r}   r   r   r   r   r   r   r   r   r   r   classmethodr   r   r   r   r%   r   __static_attributes__r^   r9   r2   r   r      sq	    H !%,0#'%)7;^$ ^$^$ ^$ *	^$
 !^$ #^$ 5^$ ^$@    "	, " $($((
 $((
!(
 !(
 	(

 "(
 !(
 (
 
(
Z $($((
 $((
%(
 !(
 	(

 "(
 !(
 (
 
(
Z +/#'$(= $(== (= !	=
 = "= != = 
=D +/#'$(= $(== (= !	=
 = "= != = 
=D  $	
 $(

 
 	
 !
 
 
&
8  $	
 $(

 
 	
 !
 
 
&
2"  $	#. $(#.*#. #. 	#. !#. #. 
&#.P  $	#. $(#.*#. #. 	#. !#. #. 
&#.P  $	3 $(33 3 	3 !3 3 
38  $	3 $(33 3 	3 !3 3 
38  $	3 $(3*3 3 	3 !3 3 
38  $	3 $(3*3 3 	3 !3 3 
38  $	
 $(

 
 	
 !
 
 
&
&  $	
 $(

 
 	
 !
 
 
&
&   $A
 $(A
*A
 A
 	A

 A
 A
 !A
 A
 
A
L   $B
 $(B
*B
 B
 	B

 B
 B
 !B
 B
 
B
N   $'
 $('
'
 '
 	'

 '
 '
 !'
 '
 
'
X   $'
 $('
'
 '
 	'

 '
 '
 !'
 '
 
'
R 
 +/#'$(!%,0#'%)1 11 1 (	1
 !1 "1 1 1 1 *1 !1 #1 1 1  
!1 1f 
 +/#'$(!%,0#'%)1 11 1 (	1
 !1 "1 1 1 1 *1 !1 #1 1 1  
!1 1j $(%)$(	 $(  # "	 !  
B $(%)$(	 $(  # "	 !  
>
"
.r9   r   )"
__future__r   loggingr`   typingr   r   r   r   r   r	   r
   r   numpyr   langchain_core.documentsr   langchain_core.embeddingsr   langchain_core.utils.iterr   langchain_core.vectorstoresr   &langchain_community.vectorstores.utilsr   r   r   r   upstash_vector.typesr   	getLoggerr   r$   r   r^   r9   r2   <module>r     sT    "   S S S  - 0 3 3 0/			8	$[. [.r9   