o g:A@sdZddlmZddlZddlmZmZddlmZddl m Z m Z m Z ddl mZddlmZmZdd lmZdd lmZdd lmZmZmZmZdd lmZe r\dd lmZmZm Z e!Z"e#eZ$ee"e$fZ%ee e$fZ&GdddeddZ'Gdddee"e$feZ(dS)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 TypedDict) deprecated)Document)RunnableRunnableConfigRunnableSerializable ensure_config)run_in_executor)#AsyncCallbackManagerForRetrieverRunCallbackManagerForRetrieverRun Callbacksc@s8eZdZUdZded< ded< ded< ded<dS) LangSmithRetrieverParamsz!LangSmith parameters for tracing.strls_retriever_name Optional[str]ls_vector_store_providerls_embedding_providerls_embedding_modelN)__name__ __module__ __qualname____doc____annotations__r"r"U/var/www/html/chatdoc2/venv/lib/python3.10/site-packages/langchain_core/retrievers.pyr7s rF)totalcseZdZUdZeddZdZded<dZded<dZ d ed < dZ d ed < d5fdd Z d6ddZ d7d8ddZ d7d8ddZed9d"d#Zd:d%d&Zed'd(d)d*ddddd+d;d0d1Zed'd2d)d*ddddd+d;d3d4ZZS)< BaseRetrievera? Abstract 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 from typing import List 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]]metadatakwargsrreturnNonec stjdi||jtjkr!tjdtdd|j}tj|_||_t|dr>|j tj kr>tjdtdd|j }tj |_ ||_ t |jj }| ddu|_|js]|j tj kr]dd d}||_ tt|hddk|_dS)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_managerselfr queryrr/list[Document]cstd|j|IdHSN)r_get_relevant_documents)r5r6r"r"r#_aget_relevant_documentsszABaseRetriever.__init_subclass__.._aget_relevant_documents>r5r6r4rr")r5r r6rr/r7)super__init_subclass__get_relevant_documentsr%warningswarnDeprecationWarningr9hasattrr3r:r parametersgetr(lensetkeysr))clsr.swapaswaprBr: __class__r"r#r<s@     zBaseRetriever.__init_subclass__rcKsL|}|dr|dd}n |dr|dd}|}t|d}|S)z Get standard params for tracing. Retriever Ni)r)get_name startswithendswithlowerr)r5r.default_retriever_name ls_paramsr"r"r#_get_ls_paramss    zBaseRetriever._get_ls_paramsinputrconfigOptional[RunnableConfig]r7c Ksddlm}t|}i|dpi|jdi|}|j|dd|dd|d|j||jd }|jd||d p?| | d dd }z!|j rM|ni}|j r^|j |fd |i|} n |j |fi|} Wntyz} z|| d} ~ ww|| | S)aInvoke 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") r)CallbackManagerr- callbacksNverboseFr+rZinheritable_tags local_tagsinheritable_metadatalocal_metadatarun_namerun_idnamerar4r") langchain_core.callbacks.managerrXrrCrT configurer+r-on_retriever_startrNpopr)r(r9 Exceptionon_retriever_erroron_retriever_end) r5rUrVr.rXr^callback_managerr4_kwargsresulter"r"r#invokesV      zBaseRetriever.invokec s$ddlm}t|}i|dpi|jdi|}|j|dd|dd|d|j||jd }|jd||d p@| | d dd IdH}z'|j rQ|ni}|j re|j |fd |i|IdH} n |j |fi|IdH} Wnty} z || IdHd} ~ ww|| IdH| S)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") r)AsyncCallbackManagerr-rYNrZFr+r[r`rarbr4r")rdrprrCrTrer+r-rfrNrgr)r(r:rhrirj) r5rUrVr.rpr^rkr4rlrmrnr"r"r#ainvokesX       zBaseRetriever.ainvoker6r4rcCsdS)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"r5r6r4r"r"r#r9Psz%BaseRetriever._get_relevant_documentsrcstd|j||dIdHS)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)r4)rr9get_syncrrr"r"r#r:^s  z&BaseRetriever._aget_relevant_documentsz0.1.46roz1.0)since alternativeremoval)rYr+r-r`rYrr`rcKsHi}|r||d<|r||d<|r||d<|r||d<|j||fi|S)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. rYr+r-r`)ror5r6rYr+r-r`r.rVr"r"r#r=ps!z$BaseRetriever.get_relevant_documentsrqcsPi}|r ||d<|r||d<|r||d<|r||d<|j||fi|IdHS)aAsynchronously 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. rYr+r-r`N)rqrwr"r"r#r3s!z%BaseRetriever.aget_relevant_documents)r.rr/r0)r.rr/rr8)rUrrVrWr.rr/r7)r6rr4rr/r7)r6rr4rr/r7)r6rrYrr+r*r-r,r`rr.rr/r7)rrrr r model_configr(r!r)r+r-r<rTrorqrr9r:r r=r3 __classcell__r"r"rJr#r%Ds@ =     2 ? ?   +r%))r __future__rr>abcrrinspectrtypingrrrpydanticr typing_extensionsr r langchain_core._apir langchain_core.documentsr langchain_core.runnablesrrrrlangchain_core.runnables.configrrdrrrrRetrieverInputlistRetrieverOutput RetrieverLikeRetrieverOutputLikerr%r"r"r"r#s(