langchain Architecture Docs
Home / Function/ _format_violation_message() — langchain Function Reference

_format_violation_message() — langchain Function Reference

Architecture documentation for the _format_violation_message() function in openai_moderation.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

Dependency Diagram

graph TD
  033a3f7e_bdfd_a614_a8dc_e4e3a07e50fd["_format_violation_message()"]
  48713c67_3a9a_ec9e_ec74_46e6955f07bd["OpenAIModerationMiddleware"]
  033a3f7e_bdfd_a614_a8dc_e4e3a07e50fd -->|defined in| 48713c67_3a9a_ec9e_ec74_46e6955f07bd
  59081f65_8455_8937_22b3_f7febac7b501["_apply_violation()"]
  59081f65_8455_8937_22b3_f7febac7b501 -->|calls| 033a3f7e_bdfd_a614_a8dc_e4e3a07e50fd
  style 033a3f7e_bdfd_a614_a8dc_e4e3a07e50fd fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/middleware/openai_moderation.py lines 440–461

    def _format_violation_message(self, content: str, result: Moderation) -> str:
        # Convert categories to dict and filter for flagged items
        categories_dict = result.categories.model_dump()
        categories = [
            name.replace("_", " ")
            for name, flagged in categories_dict.items()
            if flagged
        ]
        category_label = (
            ", ".join(categories) if categories else "OpenAI's safety policies"
        )
        template = self.violation_message or DEFAULT_VIOLATION_TEMPLATE
        scores_json = json.dumps(result.category_scores.model_dump(), sort_keys=True)
        try:
            message = template.format(
                categories=category_label,
                category_scores=scores_json,
                original_content=content,
            )
        except KeyError:
            message = template
        return message

Domain

Subdomains

Defined In

Called By

Source

Frequently Asked Questions

What does _format_violation_message() do?
_format_violation_message() is a function in the langchain codebase, defined in libs/partners/openai/langchain_openai/middleware/openai_moderation.py.
Where is _format_violation_message() defined?
_format_violation_message() is defined in libs/partners/openai/langchain_openai/middleware/openai_moderation.py at line 440.
What calls _format_violation_message()?
_format_violation_message() is called by 1 function(s): _apply_violation.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free