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

test_count_tokens_approximately_with_custom_image_penalty() — langchain Function Reference

Architecture documentation for the test_count_tokens_approximately_with_custom_image_penalty() function in test_utils.py from the langchain codebase.

Function python CoreAbstractions MessageSchema

Entity Profile

Dependency Diagram

graph TD
  8955e9da_c5c6_376e_67ed_e46cfe41e331["test_count_tokens_approximately_with_custom_image_penalty()"]
  ea3f8d89_f44b_6738_3cb9_a740a73cfca4["test_utils.py"]
  8955e9da_c5c6_376e_67ed_e46cfe41e331 -->|defined in| ea3f8d89_f44b_6738_3cb9_a740a73cfca4
  style 8955e9da_c5c6_376e_67ed_e46cfe41e331 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/messages/test_utils.py lines 2813–2826

def test_count_tokens_approximately_with_custom_image_penalty() -> None:
    """Test custom tokens_per_image parameter."""
    message = HumanMessage(
        content=[
            {"type": "text", "text": "test"},
            {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,XYZ"}},
        ]
    )

    # Using custom image penalty (e.g., for Anthropic models)
    token_count = count_tokens_approximately([message], tokens_per_image=1600)

    # Should be ~1600 (image) + ~1 (text) + 3 (extra) = ~1604 tokens
    assert 1600 < token_count < 1610

Domain

Subdomains

Defined In

Source

Frequently Asked Questions

What does test_count_tokens_approximately_with_custom_image_penalty() do?
test_count_tokens_approximately_with_custom_image_penalty() is a function in the langchain codebase, defined in libs/core/tests/unit_tests/messages/test_utils.py.
Where is test_count_tokens_approximately_with_custom_image_penalty() defined?
test_count_tokens_approximately_with_custom_image_penalty() is defined in libs/core/tests/unit_tests/messages/test_utils.py at line 2813.

Analyze Your Own Codebase

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

Try Supermodel Free