VectorstoreIndexCreator Class — langchain Architecture

Source Code

libs/langchain/langchain_classic/indexes/vectorstore.py lines 193–271

class VectorstoreIndexCreator(BaseModel):
    """Logic for creating indexes."""

    vectorstore_cls: type[VectorStore] = Field(
        default_factory=_get_in_memory_vectorstore,
    )
    embedding: Embeddings
    text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter)
    vectorstore_kwargs: dict = Field(default_factory=dict)

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
        extra="forbid",
    )

    def from_loaders(self, loaders: list[BaseLoader]) -> VectorStoreIndexWrapper:
        """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.
        """
        docs = []
        for loader in loaders:
            docs.extend(loader.load())
        return self.from_documents(docs)

    async def afrom_loaders(self, loaders: list[BaseLoader]) -> VectorStoreIndexWrapper:
        """Asynchronously 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.
        """
        docs = []
        for loader in loaders:
            docs.extend([doc async for doc in loader.alazy_load()])
        return await self.afrom_documents(docs)

    def from_documents(self, documents: list[Document]) -> VectorStoreIndexWrapper:
        """Create a `VectorStore` index from a list of documents.

        Args:
            documents: A list of `Document` objects.

        Returns:
            A `VectorStoreIndexWrapper` containing the constructed vectorstore.
        """
        sub_docs = self.text_splitter.split_documents(documents)
        vectorstore = self.vectorstore_cls.from_documents(
            sub_docs,
            self.embedding,
            **self.vectorstore_kwargs,
        )
        return VectorStoreIndexWrapper(vectorstore=vectorstore)

    async def afrom_documents(
        self,
        documents: list[Document],
    ) -> VectorStoreIndexWrapper:
        """Asynchronously create a `VectorStore` index from a list of documents.

        Args:
            documents: A list of `Document` objects.

        Returns:
            A `VectorStoreIndexWrapper` containing the constructed vectorstore.
        """
        sub_docs = self.text_splitter.split_documents(documents)
        vectorstore = await self.vectorstore_cls.afrom_documents(
            sub_docs,
            self.embedding,
            **self.vectorstore_kwargs,
        )
        return VectorStoreIndexWrapper(vectorstore=vectorstore)