dh FSSKJr SSKrSSKrSSKrSSKJr SSKJr SSK J r J r J r J r JrJrJr SSKrSSKJr SSKJr SSKJr SS KJr SS KJr SS KJr SS KJ r \!"/S Q5r"Sr#SSjr$"SS\5r%g)) annotationsN) ConfigParser)Path)AnyCallableDictIterableListOptionalTuple)Document) Embeddings guard_import) VectorStore)Docstore)InMemoryDocstore)maximal_marginal_relevance)angular euclidean manhattanhammingdotrc[S5$)z1Import annoy if available, otherwise raise error.annoyr^/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/annoy.pydependable_annoy_importrs   rc\rSrSrSrSSjr\SSj5rSSSjjrSSjr SS S jjr SS!S jjr SS"S jjr SS#S jjr SS$S jjrSS%SjjrS&S'SjjrS&S(Sjjr\S\SS4S)Sjj5r\S\SS4S*Sjj5r\S\SS4S+Sjj5rS,S-Sjjr\SS.S.Sjj5rSrg)/Annoya`Annoy` vector store. To use, you should have the ``annoy`` python package installed. Example: .. code-block:: python from langchain_community.vectorstores import Annoy db = Annoy(embedding_function, index, docstore, index_to_docstore_id) c@XlX lX0lX@lXPlg)z%Initialize with necessary components.N)embedding_functionindexmetricdocstoreindex_to_docstore_id)selfr$r%r&r'r(s r__init__Annoy.__init__*s#5   $8!rcgNr)r)s r embeddingsAnnoy.embeddings9srNc [S5e)Nz=Annoy does not allow to add new data once the index is build.)NotImplementedError)r)texts metadataskwargss r add_textsAnnoy.add_texts>s " K  rc/n[X5HgupEURUnURRU5n[ U[ 5(d[ SUSU35eURXu45 Mi U$)zTurns annoy results into a list of documents and scores. Args: idxs: List of indices of the documents in the index. dists: List of distances of the documents in the index. Returns: List of Documents and scores. Could not find document for id , got )zipr(r'search isinstancer ValueErrorappend)r)idxsdistsdocsidxdist_iddocs rprocess_index_resultsAnnoy.process_index_resultsHsyT)IC++C0C--&&s+Cc8,, #B3%vcU!STT KK $ *  rc^URRXUSS9upEURXE5$a=Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. search_k: inspect up to search_k nodes which defaults to n_trees * n if not provided Returns: List of Documents most similar to the query and score for each Tsearch_kinclude_distances)r%get_nns_by_vectorrF)r) embeddingkrLr?r@s r&similarity_search_with_score_by_vector,Annoy.similarity_search_with_score_by_vector\s9jj22 8t3 ))$66rc^URRXUSS9upEURXE5$rJ)r%get_nns_by_itemrF)r)docstore_indexrPrLr?r@s r%similarity_search_with_score_by_index+Annoy.similarity_search_with_score_by_indexns9jj00 D1 ))$66rcLURU5nURXBU5nU$)a>Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. search_k: inspect up to search_k nodes which defaults to n_trees * n if not provided Returns: List of Documents most similar to the query and score for each )r$rQ)r)queryrPrLrOrAs rsimilarity_search_with_score"Annoy.similarity_search_with_scores+++E2 ::9R rc ^URXU5nUVVs/sHupgUPM snn$s snnf)aDReturn docs most similar to embedding vector. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. search_k: inspect up to search_k nodes which defaults to n_trees * n if not provided Returns: List of Documents most similar to the embedding. )rQ)r)rOrPrLr4docs_and_scoresrE_s rsimilarity_search_by_vector!Annoy.similarity_search_by_vectors5EE ( #22//222 )c ^URXU5nUVVs/sHupgUPM snn$s snnf)a:Return docs most similar to docstore_index. Args: docstore_index: Index of document in docstore k: Number of Documents to return. Defaults to 4. search_k: inspect up to search_k nodes which defaults to n_trees * n if not provided Returns: List of Documents most similar to the embedding. )rV)r)rUrPrLr4r]rEr^s rsimilarity_search_by_index Annoy.similarity_search_by_indexs5DD x #22//222rac ^URXU5nUVVs/sHupgUPM snn$s snnf)a,Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. search_k: inspect up to search_k nodes which defaults to n_trees * n if not provided Returns: List of Documents most similar to the query. )rZ)r)rYrPrLr4r]rEr^s rsimilarity_searchAnnoy.similarity_searchs0;;EhO"12//222rac  URRXSSS9nUVs/sHopRRU5PM nn[[R "U/[R S9UUUS9n U Vs/sHowS:wdM XgPM n n/n U HdnURUn URRU 5n [U [5(d[SU SU 35eU RU 5 Mf U $s snfs snf)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: embedding: Embedding to look up documents similar to. fetch_k: Number of Documents to fetch to pass to MMR algorithm. k: Number of Documents to return. Defaults to 4. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. Returns: List of Documents selected by maximal marginal relevance. rHFrK)dtype)rP lambda_multr8r9)r%rNget_item_vectorrnparrayfloat32r(r'r;r<r r=r>)r)rOrPfetch_krjr4r?ir. mmr_selectedselected_indicesrArDrEs r'max_marginal_relevance_search_by_vector-Annoy.max_marginal_relevance_search_by_vectors2zz++ u, >BBTjj003T B1 HHi[ 3 #  .:E\"WGDG\E!A++A.C--&&s+Cc8,, #B3%vcU!STT KK  "  #CFs#C;7DDc HURU5nURXbX4S9nU$)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. Returns: List of Documents selected by maximal marginal relevance. )rj)r$rs)r)rYrProrjr4rOrAs rmax_marginal_relevance_search#Annoy.max_marginal_relevance_searchs50++E2 ;; '<  rdc U[;a[SUS[[535e[S5n U(d [S5e[ US5n U R XS9n [ U5HupU RX5 M U RXgS9 /n[ U5H+upU(aXLO0nUR[UUS95 M- [[ U55V s0sH!o[[R"55_M# nn [[ U5V Vs0sH un nUU U_M snn 5nU"UR XUU5$s sn fs snn f) NzUnsupported distance metric: z. Expected one of rz/embeddings must be provided to build AnnoyIndexrr&)n_jobs) page_contentmetadata) INDEX_METRICSr=listrlen AnnoyIndex enumerateadd_itembuildr>r rangestruuiduuid4r embed_query)clsr2r.rOr3r&treesr{r4rfr%rpemb documentstextr} index_to_idrEr's r__from Annoy.__fromsS  &3F8<''+M':&;=  W%NO O  1    2 +FA NN1 ", E )  'GA'0y|bH   X4(K L(6;3y>5JK5J#djjl++5J K#/8/C D/CVQ[^S /C D 9((%;OO L Ds )'E%E c PURU5nUR"XX#XEU40UD6$)aPConstruct Annoy wrapper from raw documents. Args: texts: List of documents to index. embedding: Embedding function to use. metadatas: List of metadata dictionaries to associate with documents. metric: Metric to use for indexing. Defaults to "angular". trees: Number of trees to use for indexing. Defaults to 100. n_jobs: Number of jobs to use for indexing. Defaults to -1. This is a user friendly interface that: 1. Embeds documents. 2. Creates an in memory docstore 3. Initializes the Annoy database This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Annoy from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() index = Annoy.from_texts(texts, embeddings) )embed_documents _Annoy__from) rr2rOr3r&rr{r4r.s r from_textsAnnoy.from_texts<s7H..u5 zz yVF NT  rc UVs/sHoSPM n nUVs/sHoSPM n nUR"XX#XEU40UD6$s snfs snf)aConstruct Annoy wrapper from embeddings. Args: text_embeddings: List of tuples of (text, embedding) embedding: Embedding function to use. metadatas: List of metadata dictionaries to associate with documents. metric: Metric to use for indexing. Defaults to "angular". trees: Number of trees to use for indexing. Defaults to 100. n_jobs: Number of jobs to use for indexing. Defaults to -1 This is a user friendly interface that: 1. Creates an in memory docstore with provided embeddings 2. Initializes the Annoy database This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Annoy from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() text_embeddings = embeddings.embed_documents(texts) text_embedding_pairs = list(zip(texts, text_embeddings)) db = Annoy.from_embeddings(text_embedding_pairs, embeddings) r)r) rtext_embeddingsrOr3r&rr{r4tr2r.s rfrom_embeddingsAnnoy.from_embeddingses[J //!1/$34OqdO 4zz yVF NT  04s = AFc[U5n[R"USS9 [5nURR UR S.US'URR[US- 5US9 [US- S5n[R"URURU4U5 S S S 5 g !,(df  g =f) zSave Annoy index, docstore, and index_to_docstore_id to disk. Args: folder_path: folder path to save index, docstore, and index_to_docstore_id to. prefault: Whether to pre-load the index into memory. T)exist_ok)rr&ANNOY index.annoy)prefault index.pklwbN)rosmakedirsrr%rr&saveropenpickledumpr'r()r) folder_pathrpath config_objectfiles r save_localAnnoy.save_localsK  D4($ kk" g D=01HE $$d +t KK(A(A=QSW X, + +s /B>> C )allow_dangerous_deserializationcU(d [S5e[U5n[S5n[US- S5n[R "U5unnn SSS5 [ W SS5n U SSn URXS 9n U R [US - 55 U"URXWW5$!,(df  Nh=f) aLoad Annoy index, docstore, and index_to_docstore_id to disk. Args: folder_path: folder path to load index, docstore, and index_to_docstore_id from. embeddings: Embeddings to use when generating queries. allow_dangerous_deserialization: whether to allow deserialization of the data which involves loading a pickle file. Pickle files can be modified by malicious actors to deliver a malicious payload that results in execution of arbitrary code on your machine. aBThe de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization. If you do this, make sure that you trust the source of the data. For example, if you are loading a file that you created, and know that no one else has modified the file, then this is safe to do. Do not set this to `True` if you are loading a file from an untrusted source (e.g., some random site on the internet.).rrrbNrrr&rzr) r=rrrrloadintrrr) rrr.rrrrr'r(rrr&r%s r load_localAnnoy.load_locals(/ "  K W% $$d +t    $ ,  g&s+ ,w'1   2 3tm+,-  " "E8=Q  !, +s B55 C)r'r$r%r(r&) r$rr%rr&rr'rr(zDict[int, str])returnzOptional[Embeddings]r-)r2z Iterable[str]r3Optional[List[dict]]r4rr List[str])r?z List[int]r@ List[float]rList[Tuple[Document, float]])rH)rOrrPrrLrrr)rUrrPrrLrrr)rYrrPrrLrrr) rOrrPrrLrr4rrList[Document]) rUrrPrrLrr4rrr) rYrrPrrLrr4rrr)rg?) rOrrPrrorrjfloatr4rrr) rYrrPrrorrjrr4rrr)r2rr.zList[List[float]]rOrr3rr&rrrr{rr4rrr!)r2rrOrr3rr&rrrr{rr4rrr!)rzList[Tuple[str, List[float]]]rOrr3rr&rrrr{rr4rrr!)F)rrrboolrNone)rrr.rrrrr!)__name__ __module__ __qualname____firstlineno____doc__r*propertyr.r5rFrQrVrZr_rcrfrsrv classmethodDEFAULT_METRICrrrrr__static_attributes__rrrr!r!s  9$ 9 9 9  9 - 9+/  (     &1 %*CE7$7),7rs[" %GGG-0-36CMQR !  K r