Home / Function/ test_json_output_key_tools_parser_multiple_matching_tools() — langchain Function Reference

test_json_output_key_tools_parser_multiple_matching_tools() — langchain Function Reference

Architecture documentation for the test_json_output_key_tools_parser_multiple_matching_tools() function in test_openai_tools.py from the langchain codebase.

Entity Profile

Dependency Diagram

graph TD
  39649c8d_e512_5491_7dd9_d94ca30bcacd["test_json_output_key_tools_parser_multiple_matching_tools()"]
  0f94a062_f577_31c7_fb9c_0f526b273e64["test_openai_tools.py"]
  39649c8d_e512_5491_7dd9_d94ca30bcacd -->|defined in| 0f94a062_f577_31c7_fb9c_0f526b273e64
  style 39649c8d_e512_5491_7dd9_d94ca30bcacd fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/output_parsers/test_openai_tools.py lines 595–651

def test_json_output_key_tools_parser_multiple_matching_tools(
    *, use_tool_calls: bool
) -> None:
    def create_message() -> AIMessage:
        tool_calls_data = [
            {
                "id": "call_func1",
                "function": {"name": "func", "arguments": '{"a":1}'},
                "type": "function",
            },
            {
                "id": "call_other",
                "function": {"name": "other", "arguments": '{"b":2}'},
                "type": "function",
            },
            {
                "id": "call_func2",
                "function": {"name": "func", "arguments": '{"a":3}'},
                "type": "function",
            },
        ]

        if use_tool_calls:
            return AIMessage(
                content="",
                tool_calls=[
                    {"id": "call_func1", "name": "func", "args": {"a": 1}},
                    {"id": "call_other", "name": "other", "args": {"b": 2}},
                    {"id": "call_func2", "name": "func", "args": {"a": 3}},
                ],
            )
        return AIMessage(
            content="",
            additional_kwargs={"tool_calls": tool_calls_data},
        )

    result = [ChatGeneration(message=create_message())]

    # Test with first_tool_only=True - should return first matching
    parser = JsonOutputKeyToolsParser(
        key_name="func", first_tool_only=True, return_id=True
    )
    output = parser.parse_result(result)  # type: ignore[arg-type]

    assert output is not None
    assert output["type"] == "func"
    assert output["args"] == {"a": 1}  # First matching tool call

    # Test with first_tool_only=False - should return all matching
    parser_all = JsonOutputKeyToolsParser(
        key_name="func", first_tool_only=False, return_id=True
    )
    output_all = parser_all.parse_result(result)  # type: ignore[arg-type]

    assert len(output_all) == 2
    assert output_all[0]["args"] == {"a": 1}
    assert output_all[1]["args"] == {"a": 3}

Domain

Subdomains

Frequently Asked Questions

What does test_json_output_key_tools_parser_multiple_matching_tools() do?
test_json_output_key_tools_parser_multiple_matching_tools() is a function in the langchain codebase, defined in libs/core/tests/unit_tests/output_parsers/test_openai_tools.py.
Where is test_json_output_key_tools_parser_multiple_matching_tools() defined?
test_json_output_key_tools_parser_multiple_matching_tools() is defined in libs/core/tests/unit_tests/output_parsers/test_openai_tools.py at line 595.

Analyze Your Own Codebase

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

Try Supermodel Free