a ag/%@sdZddlmZmZmZmZmZddlmZddl m Z ddl m Z ddl mZddlmZddlmZmZdd lmZmZmZdd lmZdd lmZed d dZGdddeZeed ddZGdddeZdS)z'Vectorstore stubs for the indexing api.)AnyDictListOptionalType) BaseLoader)Document) Embeddings)BaseLanguageModel) VectorStore)RecursiveCharacterTextSplitter TextSplitter) BaseModel ConfigDictField)RetrievalQAWithSourcesChain) RetrievalQA)returncCs tdddS)z=Return the default text splitter used for chunking documents.ir) chunk_sizeZ chunk_overlap)r rrk/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain/indexes/vectorstore.py_get_default_text_splittersrc@seZdZUdZeed<edddZdee e e e ee fe eddd Z dee e e e ee fe edd d Zdee e e e ee fe edd d Zdee e e e ee fe edddZdS)VectorStoreIndexWrapperz-Wrapper around a vectorstore for easy access. vectorstoreTforbidZarbitrary_types_allowedextraN)questionllmretriever_kwargskwargsrcKsR|durtd|pi}tj|fd|jjfi|i|}||j|i|jS)aQuery the vectorstore using the provided LLM. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: The result string from the RetrievalQA chain. NThis API has been changed to require an LLM. Please provide an llm to use for querying the vectorstore. For example, from langchain_openai import OpenAI llm = OpenAI(temperature=0) retriever)NotImplementedErrorrfrom_chain_typer as_retrieverinvoke input_key output_keyselfrrrr chainrrrquery szVectorStoreIndexWrapper.querycsX|durtd|pi}tj|fd|jjfi|i|}||j|iIdH|jS)aAsynchronously query the vectorstore using the provided LLM. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: The asynchronous result string from the RetrievalQA chain. Nr!r")r#rr$rr%ainvoker'r(r)rrraquery@szVectorStoreIndexWrapper.aquerycKsL|durtd|pi}tj|fd|jjfi|i|}||j|iS)aQuery the vectorstore and retrieve the answer along with sources. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: A dictionary containing the answer and source documents. Nr!r")r#rr$rr%r& question_keyr)rrrquery_with_sources`sz*VectorStoreIndexWrapper.query_with_sourcescsR|durtd|pi}tj|fd|jjfi|i|}||j|iIdHS)aAsynchronously query the vectorstore and retrieve the answer and sources. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: A dictionary containing the answer and source documents. Nr!r")r#rr$rr%r-r/r)rrraquery_with_sourcessz+VectorStoreIndexWrapper.aquery_with_sources)NN)NN)NN)NN)__name__ __module__ __qualname____doc__r __annotations__r model_configstrrr rrr,r.dictr0r1rrrrrsT  # # #rcCsBddl}zddlm}Wnty2tdYn0|d|S)zGet the InMemoryVectorStore.rN)InMemoryVectorStorezBPlease install langchain-community to use the InMemoryVectorStore.zUsing InMemoryVectorStore as the default vectorstore.This memory store won't persist data. You should explicitlyspecify a vectorstore when using VectorstoreIndexCreator)warningsZ)langchain_community.vectorstores.inmemoryr: ImportErrorwarn)r;r:rrr_get_in_memory_vectorstores  r>c@seZdZUdZeedZeee d<e e d<ee dZ e e d<eedZee d<eddd Zeeed d d Zeeed d dZeeedddZeeedddZdS)VectorstoreIndexCreatorzLogic for creating indexes.)default_factoryvectorstore_cls embedding text_splittervectorstore_kwargsTrr)loadersrcCs&g}|D]}||q||S)zCreate a vectorstore index from a list of loaders. Args: loaders: A list of `BaseLoader` instances to load documents. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. )extendloadfrom_documents)r*rEdocsloaderrrr from_loaderss z$VectorstoreIndexCreator.from_loaderscs@g}|D]&}|2z3dHW}||q6q||IdHS)aAsynchronously create a vectorstore index from a list of loaders. Args: loaders: A list of `BaseLoader` instances to load documents. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. N)Z alazy_loadappendafrom_documents)r*rErIrJdocrrr afrom_loaderss z%VectorstoreIndexCreator.afrom_loaders) documentsrcCs0|j|}|jj||jfi|j}t|dS)zCreate a vectorstore index from a list of documents. Args: documents: A list of `Document` objects. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. r)rCsplit_documentsrArHrBrDrr*rPZsub_docsrrrrrHs z&VectorstoreIndexCreator.from_documentscs6|j|}|jj||jfi|jIdH}t|dS)zAsynchronously create a vectorstore index from a list of documents. Args: documents: A list of `Document` objects. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. NrQ)rCrRrArMrBrDrrSrrrrMs  z'VectorstoreIndexCreator.afrom_documentsN)r2r3r4r5rr>rArr r6r rrCr r9rDrr7rrrrKrOrrHrMrrrrr?s" r?N) r5typingrrrrrZlangchain_core.document_loadersrZlangchain_core.documentsrZlangchain_core.embeddingsr Zlangchain_core.language_modelsr Zlangchain_core.vectorstoresr Zlangchain_text_splittersr r ZpydanticrrrZ*langchain.chains.qa_with_sources.retrievalrZ"langchain.chains.retrieval_qa.baserrrr>r?rrrrs