_get_base64_from_url() — langchain Function Reference

Architecture documentation for the _get_base64_from_url() function in chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ _get_base64_from_url() — langchain Function Reference

Dependency Diagram

graph TD
  a116da61_b432_7c0f_6f42_237547519f1f["_get_base64_from_url()"]
  c97ed773_97f8_2190_c0e8_546293fe345b["chat_models.py"]
  a116da61_b432_7c0f_6f42_237547519f1f -->|defined in| c97ed773_97f8_2190_c0e8_546293fe345b
  c7be2f2e_b4e7_5993_9336_e4040cb24467["test_audio_inputs()"]
  c7be2f2e_b4e7_5993_9336_e4040cb24467 -->|calls| a116da61_b432_7c0f_6f42_237547519f1f
  style a116da61_b432_7c0f_6f42_237547519f1f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/standard-tests/langchain_tests/integration_tests/chat_models.py lines 143–155

def _get_base64_from_url(url: str) -> str:
    user_agent = os.environ.get("LANGCHAIN_TESTS_USER_AGENT")
    if not user_agent:
        warning_message = (
            "LANGCHAIN_TESTS_USER_AGENT environment variable not set. "
            "langchain-tests pulls (CC0 License) audio data from wikimedia.org. "
            "Consider setting a user agent to identify your requests. See "
            "https://foundation.wikimedia.org/wiki/Policy:Wikimedia_Foundation_User-Agent_Policy"
        )
        warnings.warn(warning_message, stacklevel=2)
    headers = {"User-Agent": user_agent} if user_agent else {}
    httpx_response = httpx.get(url, headers=headers).content
    return base64.b64encode(httpx_response).decode("utf-8")