_form_documents() — langchain Function Reference

Architecture documentation for the _form_documents() function in vectorstore.py from the langchain codebase.

Function python LangChainCore ApiManagement called by 2

Entity Profile

LangChainCore→ ApiManagement→ _form_documents() — langchain Function Reference

Dependency Diagram

graph TD
  63ddc667_87b8_f7b5_c5eb_c036d48e5537["_form_documents()"]
  a0031c35_ac02_c399_69d4_5bd8f0075822["VectorStoreRetrieverMemory"]
  63ddc667_87b8_f7b5_c5eb_c036d48e5537 -->|defined in| a0031c35_ac02_c399_69d4_5bd8f0075822
  9622926d_99f7_f944_5390_39317f0838df["save_context()"]
  9622926d_99f7_f944_5390_39317f0838df -->|calls| 63ddc667_87b8_f7b5_c5eb_c036d48e5537
  ee8b0145_1599_83ea_cd5a_a29d6e27f83e["asave_context()"]
  ee8b0145_1599_83ea_cd5a_a29d6e27f83e -->|calls| 63ddc667_87b8_f7b5_c5eb_c036d48e5537
  style 63ddc667_87b8_f7b5_c5eb_c036d48e5537 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/memory/vectorstore.py lines 87–102

    def _form_documents(
        self,
        inputs: dict[str, Any],
        outputs: dict[str, str],
    ) -> list[Document]:
        """Format context from this conversation to buffer."""
        # Each document should only include the current turn, not the chat history
        exclude = set(self.exclude_input_keys)
        exclude.add(self.memory_key)
        filtered_inputs = {k: v for k, v in inputs.items() if k not in exclude}
        texts = [
            f"{k}: {v}"
            for k, v in list(filtered_inputs.items()) + list(outputs.items())
        ]
        page_content = "\n".join(texts)
        return [Document(page_content=page_content)]