Home / Function/ test_convert_to_openai_messages_anthropic() — langchain Function Reference

test_convert_to_openai_messages_anthropic() — langchain Function Reference

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

Entity Profile

Dependency Diagram

graph TD
  2e9528f1_b8ee_7620_e40f_bc01b0549549["test_convert_to_openai_messages_anthropic()"]
  ea3f8d89_f44b_6738_3cb9_a740a73cfca4["test_utils.py"]
  2e9528f1_b8ee_7620_e40f_bc01b0549549 -->|defined in| ea3f8d89_f44b_6738_3cb9_a740a73cfca4
  14e6fdde_cf6a_539a_67f6_36fd8fde5d20["create_image_data()"]
  2e9528f1_b8ee_7620_e40f_bc01b0549549 -->|calls| 14e6fdde_cf6a_539a_67f6_36fd8fde5d20
  1dd19a53_952f_5baf_39c4_aa23f0cd7f59["create_base64_image()"]
  2e9528f1_b8ee_7620_e40f_bc01b0549549 -->|calls| 1dd19a53_952f_5baf_39c4_aa23f0cd7f59
  style 2e9528f1_b8ee_7620_e40f_bc01b0549549 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/messages/test_utils.py lines 1068–1156

def test_convert_to_openai_messages_anthropic() -> None:
    image_data = create_image_data()
    messages = [
        HumanMessage(
            content=[
                {
                    "type": "text",
                    "text": "Here's an image:",
                    "cache_control": {"type": "ephemeral"},
                },
                {
                    "type": "image",
                    "source": {
                        "type": "base64",
                        "media_type": "image/jpeg",
                        "data": image_data,
                    },
                },
            ]
        ),
        AIMessage(
            content=[
                {"type": "tool_use", "name": "foo", "input": {"bar": "baz"}, "id": "1"}
            ]
        ),
        HumanMessage(
            content=[
                {
                    "type": "tool_result",
                    "tool_use_id": "1",
                    "is_error": False,
                    "content": [
                        {
                            "type": "image",
                            "source": {
                                "type": "base64",
                                "media_type": "image/jpeg",
                                "data": image_data,
                            },
                        },
                    ],
                }
            ]
        ),
    ]
    result = convert_to_openai_messages(messages)
    expected = [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Here's an image:"},
                {"type": "image_url", "image_url": {"url": create_base64_image()}},
            ],
        },
        {
            "role": "assistant",
            "content": "",
            "tool_calls": [
                {
                    "type": "function",
                    "function": {
                        "name": "foo",
                        "arguments": json.dumps({"bar": "baz"}),
                    },
                    "id": "1",
                }
            ],
        },
        {
            "role": "tool",
            "content": [
                {"type": "image_url", "image_url": {"url": create_base64_image()}}
            ],
            "tool_call_id": "1",
        },
    ]
    assert result == expected

    # Test thinking blocks (pass through)
    thinking_block = {
        "signature": "abc123",

Subdomains

Frequently Asked Questions

What does test_convert_to_openai_messages_anthropic() do?
test_convert_to_openai_messages_anthropic() is a function in the langchain codebase, defined in libs/core/tests/unit_tests/messages/test_utils.py.
Where is test_convert_to_openai_messages_anthropic() defined?
test_convert_to_openai_messages_anthropic() is defined in libs/core/tests/unit_tests/messages/test_utils.py at line 1068.
What does test_convert_to_openai_messages_anthropic() call?
test_convert_to_openai_messages_anthropic() calls 2 function(s): create_base64_image, create_image_data.

Analyze Your Own Codebase

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

Try Supermodel Free