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

test_combine_llm_outputs_with_token_details() — langchain Function Reference

Architecture documentation for the test_combine_llm_outputs_with_token_details() function in test_chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

Dependency Diagram

graph TD
  4d9a6b7d_b488_60b2_7451_f6ec7dca24f8["test_combine_llm_outputs_with_token_details()"]
  5bf2e477_37e0_3e98_4042_bc609f2f7f60["test_chat_models.py"]
  4d9a6b7d_b488_60b2_7451_f6ec7dca24f8 -->|defined in| 5bf2e477_37e0_3e98_4042_bc609f2f7f60
  style 4d9a6b7d_b488_60b2_7451_f6ec7dca24f8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/groq/tests/unit_tests/test_chat_models.py lines 873–910

def test_combine_llm_outputs_with_token_details() -> None:
    """Test that _combine_llm_outputs properly combines nested token details."""
    llm = ChatGroq(model="test-model")

    llm_outputs: list[dict[str, Any] | None] = [
        {
            "token_usage": {
                "prompt_tokens": 100,
                "completion_tokens": 50,
                "total_tokens": 150,
                "input_tokens_details": {"cached_tokens": 80},
                "output_tokens_details": {"reasoning_tokens": 20},
            },
            "model_name": "test-model",
            "system_fingerprint": "fp_123",
        },
        {
            "token_usage": {
                "prompt_tokens": 200,
                "completion_tokens": 100,
                "total_tokens": 300,
                "input_tokens_details": {"cached_tokens": 150},
                "output_tokens_details": {"reasoning_tokens": 40},
            },
            "model_name": "test-model",
            "system_fingerprint": "fp_123",
        },
    ]

    result = llm._combine_llm_outputs(llm_outputs)

    assert result["token_usage"]["prompt_tokens"] == 300
    assert result["token_usage"]["completion_tokens"] == 150
    assert result["token_usage"]["total_tokens"] == 450
    assert result["token_usage"]["input_tokens_details"]["cached_tokens"] == 230
    assert result["token_usage"]["output_tokens_details"]["reasoning_tokens"] == 60
    assert result["model_name"] == "test-model"
    assert result["system_fingerprint"] == "fp_123"

Domain

Subdomains

Defined In

Source

Frequently Asked Questions

What does test_combine_llm_outputs_with_token_details() do?
test_combine_llm_outputs_with_token_details() is a function in the langchain codebase, defined in libs/partners/groq/tests/unit_tests/test_chat_models.py.
Where is test_combine_llm_outputs_with_token_details() defined?
test_combine_llm_outputs_with_token_details() is defined in libs/partners/groq/tests/unit_tests/test_chat_models.py at line 873.

Analyze Your Own Codebase

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

Try Supermodel Free