mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
21a353e9c2
- Description: Adding async method for CTransformers - Issue: I've found impossible without this code to run Websockets inside a FastAPI micro service and a CTransformers model. - Tag maintainer: Not necessary yet, I don't like to mention directly - Twitter handle: @_semoal
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
"""Test C Transformers wrapper."""
|
|
import pytest
|
|
|
|
from langchain.llms import CTransformers
|
|
from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
|
|
|
|
|
|
def test_ctransformers_call() -> None:
|
|
"""Test valid call to C Transformers."""
|
|
config = {"max_new_tokens": 5}
|
|
callback_handler = FakeCallbackHandler()
|
|
|
|
llm = CTransformers(
|
|
model="marella/gpt-2-ggml",
|
|
config=config,
|
|
callbacks=[callback_handler],
|
|
)
|
|
|
|
output = llm("Say foo:")
|
|
assert isinstance(output, str)
|
|
assert len(output) > 1
|
|
assert 0 < callback_handler.llm_streams <= config["max_new_tokens"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_ctransformers_async_inference() -> None:
|
|
config = {"max_new_tokens": 5}
|
|
callback_handler = FakeCallbackHandler()
|
|
|
|
llm = CTransformers(
|
|
model="marella/gpt-2-ggml",
|
|
config=config,
|
|
callbacks=[callback_handler],
|
|
)
|
|
|
|
output = await llm._acall(prompt="Say foo:")
|
|
assert isinstance(output, str)
|
|
assert len(output) > 1
|
|
assert 0 < callback_handler.llm_streams <= config["max_new_tokens"]
|