validate_environment() — langchain Function Reference

Architecture documentation for the validate_environment() function in llms.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ validate_environment() — langchain Function Reference

Dependency Diagram

graph TD
  eeb60890_f14d_d489_0d0f_6ec5030c0bd9["validate_environment()"]
  e9e02443_a77e_7c58_a321_32aae5e1fcd0["_AnthropicCommon"]
  eeb60890_f14d_d489_0d0f_6ec5030c0bd9 -->|defined in| e9e02443_a77e_7c58_a321_32aae5e1fcd0
  style eeb60890_f14d_d489_0d0f_6ec5030c0bd9 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/langchain_anthropic/llms.py lines 89–106

    def validate_environment(self) -> Self:
        """Validate that api key and python package exists in environment."""
        self.client = anthropic.Anthropic(
            base_url=self.anthropic_api_url,
            api_key=self.anthropic_api_key.get_secret_value(),
            timeout=self.default_request_timeout,
            max_retries=self.max_retries,
        )
        self.async_client = anthropic.AsyncAnthropic(
            base_url=self.anthropic_api_url,
            api_key=self.anthropic_api_key.get_secret_value(),
            timeout=self.default_request_timeout,
            max_retries=self.max_retries,
        )
        # Keep for backward compatibility but not used in Messages API
        self.HUMAN_PROMPT = getattr(anthropic, "HUMAN_PROMPT", None)
        self.AI_PROMPT = getattr(anthropic, "AI_PROMPT", None)
        return self