from poma.integrations.langchain import (
    PomaCheatsheetRetrieverLC,
    PomaChunksetSplitter,
    PomaFileLoader,
)

PomaFileLoader

PomaFileLoader(input_path: str | Path)

Load one file or every supported file under a directory into LangChain Document objects.

Method:

• load() -> list[Document]

PomaChunksetSplitter

PomaChunksetSplitter(
    client: PrimeCut,
    *,
    verbose: bool = False,
    **kwargs,
)

Call the POMA API for each input document and return chunkset Document objects.

Method:

• split_documents(documents: Iterable[Document]) -> list[Document]

PomaCheatsheetRetrieverLC

PomaCheatsheetRetrieverLC(
    vector_store: VectorStore,
    *,
    top_k: int = 6,
    **kwargs,
)

Wrap a LangChain vector store and return one cheatsheet Document per source document.

Use .invoke(query) through the standard LangChain retriever interface.