langchain.indexes.vectorstore.VectorstoreIndexCreator

class langchain.indexes.vectorstore.VectorstoreIndexCreator(*, vectorstore_cls: ~typing.Type[~langchain.vectorstores.base.VectorStore] = <class 'langchain.vectorstores.chroma.Chroma'>, embedding: ~langchain.embeddings.base.Embeddings = None, text_splitter: ~langchain.text_splitter.TextSplitter = None, vectorstore_kwargs: dict = None)

Bases: BaseModel

Logic for creating indexes.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param embedding: langchain.embeddings.base.Embeddings [Optional]

param text_splitter: langchain.text_splitter.TextSplitter [Optional]

param vectorstore_cls: Type[langchain.vectorstores.base.VectorStore] = <class 'langchain.vectorstores.chroma.Chroma'>

param vectorstore_kwargs: dict [Optional]

from_documents(documents: List[Document]) → VectorStoreIndexWrapper

Create a vectorstore index from documents.

from_loaders(loaders: List[BaseLoader]) → VectorStoreIndexWrapper

Create a vectorstore index from loaders.

model Config

Bases: object

Configuration for this pydantic object.

arbitrary_types_allowed = True

extra = 'forbid'

Examples using VectorstoreIndexCreator

• Apify

• HuggingFace dataset

• Spreedly

• Image captions

• Figma

• Apify Dataset

• Iugu

• Stripe

• Modern Treasury

• Question Answering Benchmarking: State of the Union Address

• Question Answering Benchmarking: Paul Graham Essay

• Agent VectorDB Question Answering Benchmarking

• QA over Documents