(
documents: list[Document],
chunk_size: int = 300,
chunk_overlap: int = 0
)
| 70 | |
| 71 | @staticmethod |
| 72 | def split_documents_2texts( |
| 73 | documents: list[Document], |
| 74 | chunk_size: int = 300, |
| 75 | chunk_overlap: int = 0 |
| 76 | ) -> list: |
| 77 | splitter = RecursiveCharacterTextSplitter( |
| 78 | chunk_size=chunk_size, |
| 79 | chunk_overlap=chunk_overlap |
| 80 | ) |
| 81 | content = "" |
| 82 | for document in documents: |
| 83 | content += document.page_content |
| 84 | return splitter.split_text(content) |
| 85 | |
| 86 | @staticmethod |
| 87 | def crawl_file(url: str) -> str: |
nothing calls this directly
no outgoing calls
no test coverage detected