_cleanup_llm_representation() — langchain Function Reference

Architecture documentation for the _cleanup_llm_representation() function in chat_models.py from the langchain codebase.

Function python CoreAbstractions MessageSchema called by 1

Entity Profile

CoreAbstractions→ MessageSchema→ _cleanup_llm_representation() — langchain Function Reference

Dependency Diagram

graph TD
  9793f2f3_1136_1a61_b521_e03eff201daf["_cleanup_llm_representation()"]
  20f4116a_d26d_2a5f_4a10_67af6940e081["chat_models.py"]
  9793f2f3_1136_1a61_b521_e03eff201daf -->|defined in| 20f4116a_d26d_2a5f_4a10_67af6940e081
  4fc37aed_deb5_e40b_e6f9_e9ec4aba8bf4["_get_llm_string()"]
  4fc37aed_deb5_e40b_e6f9_e9ec4aba8bf4 -->|calls| 9793f2f3_1136_1a61_b521_e03eff201daf
  style 9793f2f3_1136_1a61_b521_e03eff201daf fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/chat_models.py lines 1784–1806

def _cleanup_llm_representation(serialized: Any, depth: int) -> None:
    """Remove non-serializable objects from a serialized object."""
    if depth > _MAX_CLEANUP_DEPTH:  # Don't cooperate for pathological cases
        return

    if not isinstance(serialized, dict):
        return

    if (
        "type" in serialized
        and serialized["type"] == "not_implemented"
        and "repr" in serialized
    ):
        del serialized["repr"]

    if "graph" in serialized:
        del serialized["graph"]

    if "kwargs" in serialized:
        kwargs = serialized["kwargs"]

        for value in kwargs.values():
            _cleanup_llm_representation(value, depth + 1)