create_documents() — langchain Function Reference

Architecture documentation for the create_documents() function in html.py from the langchain codebase.

Function python DocumentProcessing TextSplitters calls 2 called by 1

Entity Profile

DocumentProcessing→ TextSplitters→ create_documents() — langchain Function Reference

Dependency Diagram

graph TD
  fb63895c_3000_9932_3530_3357c6736f4f["create_documents()"]
  0c8a5f97_7cb0_fe24_746d_9689c4e5426c["HTMLSectionSplitter"]
  fb63895c_3000_9932_3530_3357c6736f4f -->|defined in| 0c8a5f97_7cb0_fe24_746d_9689c4e5426c
  242347f4_37b6_e8c6_d9d5_c00530e34196["split_documents()"]
  242347f4_37b6_e8c6_d9d5_c00530e34196 -->|calls| fb63895c_3000_9932_3530_3357c6736f4f
  cdce0dab_74f2_fff9_b284_195643913ed5["split_text()"]
  fb63895c_3000_9932_3530_3357c6736f4f -->|calls| cdce0dab_74f2_fff9_b284_195643913ed5
  3a8f906a_02bf_a0ff_6dbb_2ffbc48f937d["split_text()"]
  fb63895c_3000_9932_3530_3357c6736f4f -->|calls| 3a8f906a_02bf_a0ff_6dbb_2ffbc48f937d
  style fb63895c_3000_9932_3530_3357c6736f4f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/text-splitters/langchain_text_splitters/html.py lines 406–430

    def create_documents(
        self, texts: list[str], metadatas: list[dict[Any, Any]] | None = None
    ) -> list[Document]:
        """Create a list of `Document` objects from a list of texts.

        Args:
            texts: A list of texts to be split and converted into documents.
            metadatas: Optional list of metadata to associate with each document.

        Returns:
            A list of `Document` objects.
        """
        metadatas_ = metadatas or [{}] * len(texts)
        documents = []
        for i, text in enumerate(texts):
            for chunk in self.split_text(text):
                metadata = copy.deepcopy(metadatas_[i])

                for key in chunk.metadata:
                    if chunk.metadata[key] == "#TITLE#":
                        chunk.metadata[key] = metadata["Title"]
                metadata = {**metadata, **chunk.metadata}
                new_doc = Document(page_content=chunk.page_content, metadata=metadata)
                documents.append(new_doc)
        return documents