*hFABSrSSKJr SSKrSSKJrJr SSKJr SSK J r J r J r SSK Jr SSKJrJrJr SS KJr SS KJr SS KJrJr SS KJr SS KJrJrJrJ r SSK!J"r" \ (aSSKJ#r#J$r$ \%r&\'\r(\\&\(4r)\\ \(4r*"SS\SS9r+"SS\\&\(4\5r,g)a**Retriever** class returns Documents given a text **query**. It is more general than a vector store. A retriever does not need to be able to store documents, only to return (or retrieve) it. Vector stores can be used as the backbone of a retriever, but there are other types of retrievers as well. **Class hierarchy:** .. code-block:: BaseRetriever --> Retriever # Examples: ArxivRetriever, MergerRetriever **Main helpers:** .. code-block:: RetrieverInput, RetrieverOutput, RetrieverLike, RetrieverOutputLike, Document, Serializable, Callbacks, CallbackManagerForRetrieverRun, AsyncCallbackManagerForRetrieverRun ) annotationsN)ABCabstractmethod) signature) TYPE_CHECKINGAnyOptional) ConfigDict)Self TypedDictoverride) deprecated) Callbacks)AsyncCallbackManagerCallbackManager)Document)RunnableRunnableConfigRunnableSerializable ensure_config)run_in_executor)#AsyncCallbackManagerForRetrieverRunCallbackManagerForRetrieverRuncH\rSrSr%SrS\S'S\S'S\S'S\S'S rg ) LangSmithRetrieverParams8z!LangSmith parameters for tracing.strls_retriever_name Optional[str]ls_vector_store_providerls_embedding_providerls_embedding_modelN)__name__ __module__ __qualname____firstlineno____doc____annotations____static_attributes__r#I/root/34ku/venv/lib/python3.13/site-packages/langchain_core/retrievers.pyrr8s)+++ ((%%r+rF)totalc^\rSrSr%Sr\"SS9rSrS\S'Sr S\S'S r S \S 'S r S \S '\ SU4Sjj5r SSjr\ SS Sjj5r\ SS Sjj5r\S!Sj5rS"Sjr\"SSSS9S S S S S.S#Sjj5r\"SSSS9S S S S S.S#Sjj5rSrU=r$)$ BaseRetrieverEaAbstract base class for a Document retrieval system. A retrieval system is defined as something that can take string queries and return the most 'relevant' Documents from some source. Usage: A retriever follows the standard Runnable interface, and should be used via the standard Runnable methods of `invoke`, `ainvoke`, `batch`, `abatch`. Implementation: When implementing a custom retriever, the class should implement the `_get_relevant_documents` method to define the logic for retrieving documents. Optionally, an async native implementations can be provided by overriding the `_aget_relevant_documents` method. Example: A retriever that returns the first 5 documents from a list of documents .. code-block:: python from langchain_core.documents import Document from langchain_core.retrievers import BaseRetriever class SimpleRetriever(BaseRetriever): docs: list[Document] k: int = 5 def _get_relevant_documents(self, query: str) -> list[Document]: """Return the first k documents from the list of documents""" return self.docs[:self.k] async def _aget_relevant_documents(self, query: str) -> list[Document]: """(Optional) async native implementation.""" return self.docs[:self.k] Example: A simple retriever based on a scikit-learn vectorizer .. code-block:: python from sklearn.metrics.pairwise import cosine_similarity class TFIDFRetriever(BaseRetriever, BaseModel): vectorizer: Any docs: list[Document] tfidf_array: Any k: int = 4 class Config: arbitrary_types_allowed = True def _get_relevant_documents(self, query: str) -> list[Document]: # Ip -- (n_docs,x), Op -- (n_docs,n_Feats) query_vec = self.vectorizer.transform([query]) # Op -- (n_docs,1) -- Cosine Sim with each doc results = cosine_similarity(self.tfidf_array, query_vec).reshape( (-1,) ) return [self.docs[i] for i in results.argsort()[-self.k :][::-1]] T)arbitrary_types_allowedFbool_new_arg_supported_expects_other_argsNOptional[list[str]]tagsOptional[dict[str, Any]]metadatac >[TU]"S 0UD6 UR[R:waA[R "S[ SS9 URn[RUlX l[US5(a_UR[R:waA[R "S[ SS9 URn[RUl X0l [UR5RnURS5SLUlUR(d/UR[R:XaS SjnXPl [[!UR#551Sk- 5S :Ulg) NzgRetrievers must implement abstract `_get_relevant_documents` method instead of `get_relevant_documents`) stacklevelaget_relevant_documentsziRetrievers must implement abstract `_aget_relevant_documents` method instead of `aget_relevant_documents` run_managercL# [SURU5IShvN $N7fN)r_get_relevant_documents)selfquerys r,_aget_relevant_documentsABaseRetriever.__init_subclass__.._aget_relevant_documentss#-T43O3OQVWWWWs $"$>rArBr=rr#)rAr rBrreturnlist[Document])super__init_subclass__get_relevant_documentsr/warningswarnDeprecationWarningr@hasattrr<rCr parametersgetr3lensetkeysr4)clskwargsswapaswaprNrC __class__s r,rHBaseRetriever.__init_subclass__sa !+F+  % %)M)M M MM7"   --D44  &+/ ' C2 3 3++}/T/TT MM8"   //E55  ',1 (s::;FF !+ !>d!J&&,, 0V0VV X X#& X X ,D ( JOO%&)II JQ N r+c UR5nURS5(aUSSnOURS5(aUSSnUR5n[ US9$)z Get standard params for tracing. Retriever Ni)r)get_name startswithendswithlowerr)rA_kwargsdefault_retriever_names r,_get_ls_paramsBaseRetriever._get_ls_paramsse!% ! , ,[ 9 9%;AB%? " # , ,[ 9 9%;CR%@ "!7!=!=!?':PQQr+c [U5n0URS5=(d 0EUR"S 0UD6En[R"URS5SURSS5URS5UR UUR S9nURSUURS5=(d UR5URS S5S 9nUR(aUO0nUR(aUR"U4S U0UD6nOUR"U40UD6nURU5 U$![an URU 5 eSn A ff=f) atInvoke the retriever to get relevant documents. Main entry point for synchronous retriever invocations. Args: input: The query string. config: Configuration for the retriever. Defaults to None. kwargs: Additional arguments to pass to the retriever. Returns: List of relevant documents. Examples: .. code-block:: python retriever.invoke("query") r8 callbacksNverboseFr6rfinheritable_tags local_tagsinheritable_metadatalocal_metadatarun_namerun_idnamermr=r#)rrOrbr configurer6r8on_retriever_startr\popr4r3r@on_retriever_end Exceptionon_retriever_error rAinputconfigrTrjcallback_managerr=kwargs_resultes r,invokeBaseRetriever.invokese.v& zz*%+ !!+F+ +44 JJ{ # JJy%0#ZZ/yy!5== '99  J':4==?::h- :   $ 8 8fbG&&55'26=55eGwG  ( ( M   * *1 -  sAE E" EE"c 4# [U5n0URS5=(d 0EUR"S 0UD6En[R"URS5SURSS5URS5UR UUR S9nURSUURS5=(d UR5URS S5S 9IShvN nUR(aUO0nUR(aUR"U4S U0UD6IShvN nOUR"U40UD6IShvN nURU5IShvN U$NN=N#N ![a n URU 5IShvN eSn A ff=f7f) aAsynchronously invoke the retriever to get relevant documents. Main entry point for asynchronous retriever invocations. Args: input: The query string. config: Configuration for the retriever. Defaults to None. kwargs: Additional arguments to pass to the retriever. Returns: List of relevant documents. Examples: .. code-block:: python await retriever.ainvoke("query") r8reNrfFr6rgrlrmrnr=r#)rrOrbrrpr6r8rqr\rrr4r3rCrsrtrurvs r,ainvokeBaseRetriever.ainvokes4v& zz*%+ !!+F+ 099 JJ{ # JJy%0#ZZ/yy!5== -??  J':4==?::h- @    $ 8 8fbG&&#<< '2 6=  $<E+'E%(E+E'E+FE)F%E+'E+)F+ F5F F  FFFcg)zGet documents relevant to a query. Args: query: String to find relevant documents for. run_manager: The callback handler to use. Returns: List of relevant documents. Nr#rArBr=s r,r@%BaseRetriever._get_relevant_documentsTsr+cf# [SURUUR5S9IShvN $N7f)zAsynchronously get documents relevant to a query. Args: query: String to find relevant documents for run_manager: The callback handler to use Returns: List of relevant documents N)r=)rr@get_syncrs r,rC&BaseRetriever._aget_relevant_documentsbs9%   ( ( #,,.     s (1/1z0.1.46r}z1.0)since alternativeremoval)rer6r8rlc 0nU(aX'S'U(aX7S'U(aXGS'U(aXWS'UR"X40UD6$)a}Retrieve documents relevant to a query. Users should favor using `.invoke` or `.batch` rather than `get_relevant_documents directly`. Args: query: string to find relevant documents for. callbacks: Callback manager or list of callbacks. Defaults to None. tags: Optional list of tags associated with the retriever. These tags will be associated with each call to this retriever, and passed as arguments to the handlers defined in `callbacks`. Defaults to None. metadata: Optional metadata associated with the retriever. This metadata will be associated with each call to this retriever, and passed as arguments to the handlers defined in `callbacks`. Defaults to None. run_name: Optional name for the run. Defaults to None. kwargs: Additional arguments to pass to the retriever. Returns: List of relevant documents. rer6r8rl)r}rArBrer6r8rlrTrxs r,rI$BaseRetriever.get_relevant_documentsusIB"$ "+;  !6N !):  !): {{53F33r+rc# 0nU(aX'S'U(aX7S'U(aXGS'U(aXWS'UR"X40UD6IShvN $N7f)axAsynchronously get documents relevant to a query. Users should favor using `.ainvoke` or `.abatch` rather than `aget_relevant_documents directly`. Args: query: string to find relevant documents for. callbacks: Callback manager or list of callbacks. tags: Optional list of tags associated with the retriever. These tags will be associated with each call to this retriever, and passed as arguments to the handlers defined in `callbacks`. Defaults to None. metadata: Optional metadata associated with the retriever. This metadata will be associated with each call to this retriever, and passed as arguments to the handlers defined in `callbacks`. Defaults to None. run_name: Optional name for the run. Defaults to None. kwargs: Additional arguments to pass to the retriever. Returns: List of relevant documents. rer6r8rlN)rrs r,r<%BaseRetriever.aget_relevant_documentssRB"$ "+;  !6N !):  !): \\%:6::::sAAA Ar#)rTrrENone)r`rrErr?)rwrrxzOptional[RunnableConfig]rTrrErF)rBrr=rrErF)rBrr=rrErF)rBrrerr6r5r8r7rlrrTrrErF)r$r%r&r'r(r model_configr3r)r4r6r8r rHrbr}rrr@rCrrIr<r* __classcell__)rWs@r,r/r/Es>@ $L %$ %% $D $ *.H&-0 0 d R=A99":9MP9 99v,0<<)< <  <<|    *H        *M  &hHeD $$(-1"&)4)4 )4 " )4 + )4 )4)4 )4E)4VhIuE $$(-1"&);); ); " ); + ); );); );F);r+r/)-r( __future__rrJabcrrinspectrtypingrrr pydanticr typing_extensionsr r r langchain_core._apirlangchain_core.callbacksr langchain_core.callbacks.managerrrlangchain_core.documentsrlangchain_core.runnablesrrrrlangchain_core.runnables.configrrrrRetrieverInputlistRetrieverOutput RetrieverLikeRetrieverOutputLikerr/r#r+r,rs*##//77*.R- < x.89 sO34 y F;()HI3F;r+