dh;SSKJr SSKrSSKJr SSKJr SSKJrJ r J r J r J r SSK rSSKJr SSKJr SSKJr SS KJr SS KJr \R2"\5r"S S \5rg) ) annotationsN)deepcopy)Enum)AnyIterableListOptionalTuple)Document) Embeddings)run_in_executor) VectorStore)maximal_marginal_relevancecv\rSrSrSrSSSjjr\SSj5rSSSjjr\ SSSjj5r "SS \ 5r S \ RS4SS jjrS \ RS4SS jjrS \ RS4S S jjrS \ RS4S!SjjrS"SS.S#SjjjrS$S%SjjrS&SjrS'SjrS(S)SjjrS(S)SjjrSrg)*RocksetaN`Rockset` vector store. To use, you should have the `rockset` python package installed. Note that to use this, the collection being used must already exist in your Rockset instance. You must also ensure you use a Rockset ingest transformation to apply `VECTOR_ENFORCE` on the column being used to store `embedding_key` in the collection. See: https://rockset.com/blog/introducing-vector-search-on-rockset/ for more details Everything below assumes `commons` Rockset workspace. Example: .. code-block:: python from langchain_community.vectorstores import Rockset from langchain_community.embeddings.openai import OpenAIEmbeddings import rockset # Make sure you use the right host (region) for your Rockset instance # and APIKEY has both read-write access to your collection. rs = rockset.RocksetClient(host=rockset.Regions.use1a1, api_key="***") collection_name = "langchain_demo" embeddings = OpenAIEmbeddings() vectorstore = Rockset(rs, collection_name, embeddings, "description", "description_embedding") c2SSKJn [X5(d[ S[ U535eXlX0lX lX@l XPl X`l UR RS5 g![a [S5ef=f![a gf=f)aInitialize with Rockset client. Args: client: Rockset client object collection: Rockset collection to insert docs / query embeddings: Langchain Embeddings object to use to generate embedding for given text. text_key: column in Rockset collection to use to store the text embedding_key: column in Rockset collection to use to store the embedding. Note: We must apply `VECTOR_ENFORCE()` on this column via Rockset ingest transformation. r) RocksetClient]Could not import rockset client python package. Please install it with `pip install rockset`.z;client should be an instance of rockset.RocksetClient, got langchainN)rocksetr ImportError isinstance ValueErrortype_client_collection_name _embeddings _text_key_embedding_key _workspaceset_applicationAttributeError)selfclient embeddingscollection_nametext_key embedding_key workspacers b/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/rocksetdb.py__init__Rockset.__init__1s*  -&00F|n&   /%!+#  LL ( ( 5) @  *   sA0B 0B BBcUR$N)rr$s r+r&Rockset.embeddingsasNc /n/n[U5Hup[U5U:XaXpRU5- n/n0n U(a[U5U:a [X(5n U(a[U5U:aX8U S'XUR'UR R U 5XR'URU 5 M [U5S:aXpRU5- n/nU$)aRun more texts through the embeddings and add to the vectorstore 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: Send documents in batches to rockset. Returns: List of ids from adding the texts into the vectorstore. _idr) enumeratelen_write_documents_to_rocksetrrr embed_queryr append) r$texts metadatasids batch_sizekwargsbatch stored_idsitextdocs r+ add_textsRockset.add_textses(  'GA5zZ'>>uEE CS^a/y|,s3x!| VE "& '+'7'7'C'CD'IC## $ LL ( u:> ::5A AJEr2c  UcS5eU(dS5eU(dS5eU(dS5eU"XBXVU5n U RXX5 U $)z^Create Rockset wrapper with existing texts. This is intended as a quicker way to get started. zRockset Client cannot be NonezCollection name cannot be emptyzText key name cannot be emptyzEmbedding key cannot be empty)rD) clsr: embeddingr;r%r'r(r)r<r=r>rs r+ from_textsRockset.from_textssc&!B#BB!A AA888x===}fMR%C<r2c*\rSrSrSrSrSrSSjrSrg) Rockset.DistanceFunction COSINE_SIMEUCLIDEAN_DIST DOT_PRODUCTc&URS:Xagg)NrOASCDESC)valuer0s r+order_by!Rockset.DistanceFunction.order_byszz--r2N)returnstr) __name__ __module__ __qualname____firstlineno__rNrOrPrU__static_attributes__rWr2r+DistanceFunctionrLs! )#  r2r_c `UR"URRU5UUU40UD6$)a{Perform a similarity search with Rockset Args: query (str): Text to look up documents similar to. distance_func (DistanceFunction): how to compute distance between two vectors in Rockset. k (int, optional): Top K neighbors to retrieve. Defaults to 4. where_str (Optional[str], optional): Metadata filters supplied as a SQL `where` condition string. Defaults to None. eg. "price<=70.0 AND brand='Nintendo'" NOTE: Please do not let end-user to fill this and always be aware of SQL injection. Returns: List[Tuple[Document, float]]: List of documents with their relevance score )1similarity_search_by_vector_with_relevance_scoresrr8r$queryk distance_func where_strr>s r+'similarity_search_with_relevance_scores/Rockset.similarity_search_with_relevance_scoress>2EE    ( ( /       r2c `UR"URRU5UUU40UD6$)zQSame as `similarity_search_with_relevance_scores` but doesn't return the scores. )similarity_search_by_vectorrr8rcs r+similarity_searchRockset.similarity_searchs>//    ( ( /       r2c bUR"XX440UD6nUVVs/sHupxUPM snn$s snnf)zRAccepts a query_embedding (vector), and returns documents with similar embeddings.)rb) r$rHrerfrgr>docs_and_scoresrC_s r+rk#Rockset.similarity_search_by_vectors=PP - 6< #22//222s +c *SnSU;aUSnURXX$U5nURRRSU0S9n/n URGH n 0n [U [5(dSR[U 555eU R5Hup-X R:XaC[U [5(d*SRUR[U 555eU nMWUS :Xa8[U [5(dS R[U 555eU nMUS ;dMXU'M U R![#WU S 9W45 GM U $![a"n [ R SU 5 /sSn A $Sn A ff=f) ztAccepts a query_embedding (vector), and returns documents with similar embeddings along with their relevance scores.Texclude_embeddingsrd)sqlz$Exception when querying Rockset: %s Nz;document should be of type `dict[str,Any]`. But found: `{}`zIpage content stored in column `{}` must be of type `str`. But found: `{}`distzDComputed distance between vectors must of type `float`. But found {})r4 _event_time_meta) page_contentmetadata)_build_query_sqlrQueriesrd ExceptionloggererrorresultsrdictformatritemsrrYfloatr9r )r$rHrerfrgr>rsq_strquery_responsee finalResultdocumentryvrxscores r+rb9Rockset.similarity_search_by_vector_with_relevance_scoress" 6 )!'(query_embedding initial_docsrCr&selected_indicesrAs r+max_marginal_relevance_search%Rockset.max_marginal_relevance_search0s:**66u=77  $    DPP* ooa--./  %%'() 1vh  r2cURRRURXRS9nUR Vs/sHo3R PM sn$s snf)N collectiondatar*)r Documents add_documentsrr!rr4)r$r? add_doc_res doc_statuss r+r7#Rockset._write_documents_to_rocksetsTll,,::,,5OO; 2=1A1AB1A:1ABBBsAc SSKJn URRR UR UVs/sHo2"US9PM snURS9 g![a [S5ef=fs snf)z1Delete a list of docs from the Rockset collectionr)DeleteDocumentsRequestDatar)idrN)rockset.modelsrrrrdelete_documentsrr!)r$r<rrAs r+ delete_textsRockset.delete_textssz  A //,,rs r+deleteRockset.deletesH {   c "    LLJA N s A>AcN# [SURU40UD6IShvN $N7fr/)r r)r$r<r>s r+adeleteRockset.adeletes%%T4;;FvFFFFs %#%)rrr rrr!)commons) r%rr&r r'rYr(rYr)rYr*rY)rXr )NN ) r:z Iterable[str]r;Optional[List[dict]]r<Optional[List[str]]r=intr>rrX List[str])NNrrrNr)r:rrHr r;rr%rr'rYr(rYr)rYr<rr=rr>rrXr) rdrYrerrfr_rg Optional[str]r>rrXList[Tuple[Document, float]]) rdrYrerrfr_rgrr>rrXList[Document]) rH List[float]rerrfr_rgrr>rrXr) rHrrerrfr_rgrr>rrXr)r`g?)rdrYrerrrrrrgrr>rrXr)r`NT) rrrfr_rerrgrrsboolrXrY)r?z List[dict]rXr)r<rrXNoner/)r<rr>rrXzOptional[bool])rZr[r\r]__doc__r,propertyr&rD classmethodrIrr_rNrhrlrkrbrrzr7rrrr^rWr2r+rrsvH#... .  .  ..`  +/#' &&(&! &  &  & &P +/!#'(     ! 8 4 *:*E*E#'     (  !     & H*:*E*E#'     (  !      ,*:*E*E#' 33 3( 3 ! 3  3 3&*:*E*E#' 55 5( 5 ! 5  5 &5t 4;$(4;4; 4; 4;  4;!4;4; 4;x#'#' $(   !  !  2C  *.G&G9<G GGr2r) __future__rloggingcopyrenumrtypingrrrr r numpyrlangchain_core.documentsr langchain_core.embeddingsr langchain_core.runnablesr langchain_core.vectorstoresr&langchain_community.vectorstores.utilsr getLoggerrZr}rrWr2r+rsI"77-043M   8 $RGkRGr2