langchain Architecture Docs
Home / File/ test_log.py — langchain Source File

test_log.py — langchain Source File

Architecture documentation for test_log.py, a python file in the langchain codebase. 2 imports, 0 dependents.

File python LangChainCore ApiManagement 2 imports 4 functions

Entity Profile

Dependency Diagram

graph LR
  60c70288_7962_a47f_d9f2_01467def64c3["test_log.py"]
  59e0d3b0_0f8e_4b79_d442_e9b4821561c7["langchain_core.agents"]
  60c70288_7962_a47f_d9f2_01467def64c3 --> 59e0d3b0_0f8e_4b79_d442_e9b4821561c7
  67ceb331_75bc_297f_f874_f62744fc78b8["langchain_classic.agents.format_scratchpad.log"]
  60c70288_7962_a47f_d9f2_01467def64c3 --> 67ceb331_75bc_297f_f874_f62744fc78b8
  style 60c70288_7962_a47f_d9f2_01467def64c3 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

from langchain_core.agents import AgentAction

from langchain_classic.agents.format_scratchpad.log import format_log_to_str


def test_single_agent_action_observation() -> None:
    intermediate_steps = [
        (AgentAction(tool="Tool1", tool_input="input1", log="Log1"), "Observation1"),
    ]
    expected_result = "Log1\nObservation: Observation1\nThought: "
    assert format_log_to_str(intermediate_steps) == expected_result


def test_multiple_agent_actions_observations() -> None:
    intermediate_steps = [
        (AgentAction(tool="Tool1", tool_input="input1", log="Log1"), "Observation1"),
        (AgentAction(tool="Tool2", tool_input="input2", log="Log2"), "Observation2"),
        (AgentAction(tool="Tool3", tool_input="input3", log="Log3"), "Observation3"),
    ]
    expected_result = """Log1\nObservation: Observation1\nThought: \
Log2\nObservation: Observation2\nThought: Log3\nObservation: \
Observation3\nThought: """
    assert format_log_to_str(intermediate_steps) == expected_result


def test_custom_prefixes() -> None:
    intermediate_steps = [
        (AgentAction(tool="Tool1", tool_input="input1", log="Log1"), "Observation1"),
    ]
    observation_prefix = "Custom Observation: "
    llm_prefix = "Custom Thought: "
    expected_result = "Log1\nCustom Observation: Observation1\nCustom Thought: "
    assert (
        format_log_to_str(intermediate_steps, observation_prefix, llm_prefix)
        == expected_result
    )


def test_empty_intermediate_steps() -> None:
    output = format_log_to_str([])
    assert output == ""

Domain

Subdomains

Functions

Dependencies

  • langchain_classic.agents.format_scratchpad.log
  • langchain_core.agents

Source

Frequently Asked Questions

What does test_log.py do?
test_log.py is a source file in the langchain codebase, written in python. It belongs to the LangChainCore domain, ApiManagement subdomain.
What functions are defined in test_log.py?
test_log.py defines 4 function(s): test_custom_prefixes, test_empty_intermediate_steps, test_multiple_agent_actions_observations, test_single_agent_action_observation.
What does test_log.py depend on?
test_log.py imports 2 module(s): langchain_classic.agents.format_scratchpad.log, langchain_core.agents.
Where is test_log.py in the architecture?
test_log.py is located at libs/langchain/tests/unit_tests/agents/format_scratchpad/test_log.py (domain: LangChainCore, subdomain: ApiManagement, directory: libs/langchain/tests/unit_tests/agents/format_scratchpad).

Analyze Your Own Codebase

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

Try Supermodel Free