test_trace_pdfs() — langchain Function Reference

Architecture documentation for the test_trace_pdfs() function in test_base.py from the langchain codebase.

Function python CoreAbstractions MessageSchema

Entity Profile

CoreAbstractions→ MessageSchema→ test_trace_pdfs() — langchain Function Reference

Dependency Diagram

graph TD
  df5e3a31_05b6_fca1_2e7e_82f88430149c["test_trace_pdfs()"]
  8830054d_ac1e_daa9_c6c5_ff55b10d0bf3["test_base.py"]
  df5e3a31_05b6_fca1_2e7e_82f88430149c -->|defined in| 8830054d_ac1e_daa9_c6c5_ff55b10d0bf3
  style df5e3a31_05b6_fca1_2e7e_82f88430149c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/language_models/chat_models/test_base.py lines 522–558

def test_trace_pdfs() -> None:
    # For backward compat
    llm = ParrotFakeChatModel()
    messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "file",
                    "mime_type": "application/pdf",
                    "base64": "<base64 string>",
                }
            ],
        }
    ]
    tracer = FakeChatModelStartTracer()

    with warnings.catch_warnings():
        warnings.simplefilter("error")
        llm.invoke(messages, config={"callbacks": [tracer]})

    assert tracer.messages == [
        [
            [
                HumanMessage(
                    content=[
                        {
                            "type": "file",
                            "mime_type": "application/pdf",
                            "source_type": "base64",
                            "data": "<base64 string>",
                        }
                    ]
                )
            ]
        ]
    ]