langchain Architecture Docs
Home / File/ test_langchain_v0.py — langchain Source File

test_langchain_v0.py — langchain Source File

Architecture documentation for test_langchain_v0.py, a python file in the langchain codebase. 3 imports, 0 dependents.

File python CoreAbstractions MessageSchema 3 imports 2 functions

Entity Profile

Dependency Diagram

graph LR
  587266c7_f830_435d_d973_0d64235b5d35["test_langchain_v0.py"]
  d758344f_537f_649e_f467_b9d7442e86df["langchain_core.messages"]
  587266c7_f830_435d_d973_0d64235b5d35 --> d758344f_537f_649e_f467_b9d7442e86df
  5d424099_b75b_144f_f438_6c504b51b923["langchain_core.messages.block_translators.langchain_v0"]
  587266c7_f830_435d_d973_0d64235b5d35 --> 5d424099_b75b_144f_f438_6c504b51b923
  6e27a55e_2e34_4dd3_6821_c8c2b0a67be6["tests.unit_tests.language_models.chat_models.test_base"]
  587266c7_f830_435d_d973_0d64235b5d35 --> 6e27a55e_2e34_4dd3_6821_c8c2b0a67be6
  style 587266c7_f830_435d_d973_0d64235b5d35 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

from langchain_core.messages import HumanMessage
from langchain_core.messages import content as types
from langchain_core.messages.block_translators.langchain_v0 import (
    _convert_legacy_v0_content_block_to_v1,
)
from tests.unit_tests.language_models.chat_models.test_base import (
    _content_blocks_equal_ignore_id,
)


def test_convert_to_v1_from_openai_input() -> None:
    message = HumanMessage(
        content=[
            {"type": "text", "text": "Hello"},
            {
                "type": "image",
                "source_type": "url",
                "url": "https://example.com/image.png",
            },
            {
                "type": "image",
                "source_type": "base64",
                "data": "<base64 data>",
                "mime_type": "image/png",
            },
            {
                "type": "file",
                "source_type": "url",
                "url": "<document url>",
            },
            {
                "type": "file",
                "source_type": "base64",
                "data": "<base64 data>",
                "mime_type": "application/pdf",
            },
            {
                "type": "audio",
                "source_type": "base64",
                "data": "<base64 data>",
                "mime_type": "audio/mpeg",
            },
            {
                "type": "file",
                "source_type": "id",
                "id": "<file id>",
            },
        ]
    )

    expected: list[types.ContentBlock] = [
        {"type": "text", "text": "Hello"},
        {
            "type": "image",
            "url": "https://example.com/image.png",
        },
        {
            "type": "image",
            "base64": "<base64 data>",
            "mime_type": "image/png",
        },
        {
            "type": "file",
            "url": "<document url>",
        },
        {
            "type": "file",
            "base64": "<base64 data>",
            "mime_type": "application/pdf",
        },
        {
            "type": "audio",
            "base64": "<base64 data>",
            "mime_type": "audio/mpeg",
        },
        {
            "type": "file",
            "file_id": "<file id>",
        },
    ]

    assert _content_blocks_equal_ignore_id(message.content_blocks, expected)


def test_convert_with_extras_on_v0_block() -> None:
    """Test that extras on old-style blocks are preserved in conversion.

    Refer to `_extract_v0_extras` for details.
    """
    block = {
        "type": "image",
        "source_type": "url",
        "url": "https://example.com/image.png",
        # extras follow
        "alt_text": "An example image",
        "caption": "Example caption",
        "name": "example_image",
        "description": None,
        "attribution": None,
    }
    expected_output = {
        "type": "image",
        "url": "https://example.com/image.png",
        "extras": {
            "alt_text": "An example image",
            "caption": "Example caption",
            "name": "example_image",
            # "description": None,  # These are filtered out
            # "attribution": None,
        },
    }

    assert _convert_legacy_v0_content_block_to_v1(block) == expected_output

Domain

Subdomains

Functions

Dependencies

  • langchain_core.messages
  • langchain_core.messages.block_translators.langchain_v0
  • tests.unit_tests.language_models.chat_models.test_base

Source

Frequently Asked Questions

What does test_langchain_v0.py do?
test_langchain_v0.py is a source file in the langchain codebase, written in python. It belongs to the CoreAbstractions domain, MessageSchema subdomain.
What functions are defined in test_langchain_v0.py?
test_langchain_v0.py defines 2 function(s): test_convert_to_v1_from_openai_input, test_convert_with_extras_on_v0_block.
What does test_langchain_v0.py depend on?
test_langchain_v0.py imports 3 module(s): langchain_core.messages, langchain_core.messages.block_translators.langchain_v0, tests.unit_tests.language_models.chat_models.test_base.
Where is test_langchain_v0.py in the architecture?
test_langchain_v0.py is located at libs/core/tests/unit_tests/messages/block_translators/test_langchain_v0.py (domain: CoreAbstractions, subdomain: MessageSchema, directory: libs/core/tests/unit_tests/messages/block_translators).

Analyze Your Own Codebase

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

Try Supermodel Free