langchain/libs/standard-tests
ccurme c5bf114c0f
together, standard-tests: specify tool_choice in standard tests (#25548)
Here we allow standard tests to specify a value for `tool_choice` via a
`tool_choice_value` property, which defaults to None.

Chat models [available in
Together](https://docs.together.ai/docs/chat-models) have issues passing
standard tool calling tests:
- llama 3.1 models currently [appear to rely on user-side
parsing](https://docs.together.ai/docs/llama-3-function-calling) in
Together;
- Mixtral-8x7B and Mistral-7B (currently tested) consistently do not
call tools in some tests.

Specifying tool_choice also lets us remove an existing `xfail` and use a
smaller model in Groq tests.
2024-08-19 16:37:36 -04:00
..
langchain_standard_tests together, standard-tests: specify tool_choice in standard tests (#25548) 2024-08-19 16:37:36 -04:00
scripts
tests standard-tests[patch]: Add pytest assert rewrites (#24408) 2024-07-18 21:41:11 +00:00
Makefile
poetry.lock standard-tests[minor]: Add standard tests for cache (#23357) 2024-06-24 15:15:03 +00:00
pyproject.toml standard-tests[minor]: Add standard tests for cache (#23357) 2024-06-24 15:15:03 +00:00
README.md

langchain-standard-tests

This is an INTERNAL library for the LangChain project. It contains the base classes for a standard set of tests.

Installation

This package will NOT be regularly published to pypi. It is intended to be installed directly from github at test time.

Pip:

```bash
pip install git+https://github.com/langchain-ai/langchain.git#subdirectory=libs/standard-tests
```

Poetry:

```bash
poetry add git+https://github.com/langchain-ai/langchain.git#subdirectory=libs/standard-tests
```

Usage

To add standard tests to an integration package's e.g. ChatModel, you need to create

  1. A unit test class that inherits from ChatModelUnitTests
  2. An integration test class that inherits from ChatModelIntegrationTests

tests/unit_tests/test_standard.py:

"""Standard LangChain interface tests"""

from typing import Type

import pytest
from langchain_core.language_models import BaseChatModel
from langchain_standard_tests.unit_tests import ChatModelUnitTests

from langchain_parrot_chain import ChatParrotChain


class TestParrotChainStandard(ChatModelUnitTests):
    @pytest.fixture
    def chat_model_class(self) -> Type[BaseChatModel]:
        return ChatParrotChain

tests/integration_tests/test_standard.py:

"""Standard LangChain interface tests"""

from typing import Type

import pytest
from langchain_core.language_models import BaseChatModel
from langchain_standard_tests.integration_tests import ChatModelIntegrationTests

from langchain_parrot_chain import ChatParrotChain


class TestParrotChainStandard(ChatModelIntegrationTests):
    @pytest.fixture
    def chat_model_class(self) -> Type[BaseChatModel]:
        return ChatParrotChain

Reference

The following fixtures are configurable in the test classes. Anything not marked as required is optional.

  • chat_model_class (required): The class of the chat model to be tested
  • chat_model_params: The keyword arguments to pass to the chat model constructor
  • chat_model_has_tool_calling: Whether the chat model can call tools. By default, this is set to hasattr(chat_model_class, 'bind_tools)
  • chat_model_has_structured_output: Whether the chat model can structured output. By default, this is set to hasattr(chat_model_class, 'with_structured_output')