mirror of
https://github.com/hwchase17/langchain.git
synced 2026-06-09 10:17:00 +00:00
e686a70ee0
* New `reasoning` (bool) param to support toggling [Ollama thinking](https://ollama.com/blog/thinking) (#31573, #31700). If `reasoning=True`, Ollama's `thinking` content will be placed in the model responses' `additional_kwargs.reasoning_content`. * Supported by: * ChatOllama (class level, invocation level TODO) * OllamaLLM (TODO) * Added tests to ensure streaming tool calls is successful (#29129) * Refactored tests that relied on `extract_reasoning()` * Myriad docs additions and consistency/typo fixes * Improved type safety in some spots Closes #29129 Addresses #31573 and #31700 Supersedes #31701
86 lines
2.8 KiB
Python
86 lines
2.8 KiB
Python
"""Test chat model integration."""
|
|
|
|
import json
|
|
from collections.abc import Generator
|
|
from contextlib import contextmanager
|
|
from typing import Any
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
from httpx import Client, Request, Response
|
|
from langchain_core.messages import ChatMessage
|
|
from langchain_tests.unit_tests import ChatModelUnitTests
|
|
|
|
from langchain_ollama.chat_models import ChatOllama, _parse_arguments_from_tool_call
|
|
|
|
MODEL_NAME = "llama3.1"
|
|
|
|
|
|
class TestChatOllama(ChatModelUnitTests):
|
|
@property
|
|
def chat_model_class(self) -> type[ChatOllama]:
|
|
return ChatOllama
|
|
|
|
@property
|
|
def chat_model_params(self) -> dict:
|
|
return {"model": MODEL_NAME}
|
|
|
|
|
|
def test__parse_arguments_from_tool_call() -> None:
|
|
raw_response = '{"model":"sample-model","message":{"role":"assistant","content":"","tool_calls":[{"function":{"name":"get_profile_details","arguments":{"arg_1":"12345678901234567890123456"}}}]},"done":false}' # noqa: E501
|
|
raw_tool_calls = json.loads(raw_response)["message"]["tool_calls"]
|
|
response = _parse_arguments_from_tool_call(raw_tool_calls[0])
|
|
assert response is not None
|
|
assert isinstance(response["arg_1"], str)
|
|
|
|
|
|
@contextmanager
|
|
def _mock_httpx_client_stream(
|
|
*args: Any, **kwargs: Any
|
|
) -> Generator[Response, Any, Any]:
|
|
yield Response(
|
|
status_code=200,
|
|
content='{"message": {"role": "assistant", "content": "The meaning ..."}}',
|
|
request=Request(method="POST", url="http://whocares:11434"),
|
|
)
|
|
|
|
|
|
def test_arbitrary_roles_accepted_in_chatmessages(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(Client, "stream", _mock_httpx_client_stream)
|
|
|
|
llm = ChatOllama(
|
|
model=MODEL_NAME,
|
|
verbose=True,
|
|
format=None,
|
|
)
|
|
|
|
messages = [
|
|
ChatMessage(
|
|
role="somerandomrole",
|
|
content="I'm ok with you adding any role message now!",
|
|
),
|
|
ChatMessage(role="control", content="thinking"),
|
|
ChatMessage(role="user", content="What is the meaning of life?"),
|
|
]
|
|
|
|
llm.invoke(messages)
|
|
|
|
|
|
@patch("langchain_ollama.chat_models.validate_model")
|
|
def test_validate_model_on_init(mock_validate_model: Any) -> None:
|
|
"""Test that the model is validated on initialization when requested."""
|
|
# Test that validate_model is called when validate_model_on_init=True
|
|
ChatOllama(model=MODEL_NAME, validate_model_on_init=True)
|
|
mock_validate_model.assert_called_once()
|
|
mock_validate_model.reset_mock()
|
|
|
|
# Test that validate_model is NOT called when validate_model_on_init=False
|
|
ChatOllama(model=MODEL_NAME, validate_model_on_init=False)
|
|
mock_validate_model.assert_not_called()
|
|
|
|
# Test that validate_model is NOT called by default
|
|
ChatOllama(model=MODEL_NAME)
|
|
mock_validate_model.assert_not_called()
|