github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-12 00:11:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow clearing cache and fix gptcache (#3493)

Browse Source 
This PR

* Adds `clear` method for `BaseCache` and implements it for various
caches
* Adds the default `init_func=None` and fixes gptcache integtest
* Since right now integtest is not running in CI, I've verified the
changes by running `docs/modules/models/llms/examples/llm_caching.ipynb`
(until proper e2e integtest is done in CI)
This commit is contained in:
Ehsan M. Kermani
2023-04-26 22:03:50 -07:00
committed by GitHub
parent 83e871f1ff
commit 4a246e2fd6
5 changed files with 97 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
tests/integration_tests/cache/test_gptcache.py vendored
View File

@@ -1,61 +1,48 @@
import os
from typing import Any, Callable, Optional
import pytest
import langchain
from langchain.cache import GPTCache
from langchain.schema import Generation, LLMResult
from langchain.schema import Generation
from tests.unit_tests.llms.fake_llm import FakeLLM
try:
import gptcache # noqa: F401
from gptcache import Cache # noqa: F401
from gptcache.manager.factory import get_data_manager
from gptcache.processor.pre import get_prompt
gptcache_installed = True
except ImportError:
gptcache_installed = False
def init_gptcache_map(cache_obj: Cache) -> None:
i = getattr(init_gptcache_map, "_i", 0)
cache_path = f"data_map_{i}.txt"
if os.path.isfile(cache_path):
os.remove(cache_path)
cache_obj.init(
pre_embedding_func=get_prompt,
data_manager=get_data_manager(data_path=cache_path),
)
init_gptcache_map._i = i + 1 # type: ignore
@pytest.mark.skipif(not gptcache_installed, reason="gptcache not installed")
def test_gptcache_map_caching() -> None:
"""Test gptcache caching behavior."""
from gptcache import Cache
from gptcache.manager.factory import get_data_manager
from gptcache.processor.pre import get_prompt
i = 0
file_prefix = "data_map"
def init_gptcache_map(cache_obj: Cache) -> None:
nonlocal i
cache_path = f"{file_prefix}_{i}.txt"
if os.path.isfile(cache_path):
os.remove(cache_path)
cache_obj.init(
pre_embedding_func=get_prompt,
data_manager=get_data_manager(data_path=cache_path),
)
i += 1
langchain.llm_cache = GPTCache(init_gptcache_map)
@pytest.mark.parametrize("init_func", [None, init_gptcache_map])
def test_gptcache_caching(init_func: Optional[Callable[[Any], None]]) -> None:
"""Test gptcache default caching behavior."""
langchain.llm_cache = GPTCache(init_func)
llm = FakeLLM()
params = llm.dict()
params["stop"] = None
llm_string = str(sorted([(k, v) for k, v in params.items()]))
langchain.llm_cache.update("foo", llm_string, [Generation(text="fizz")])
output = llm.generate(["foo", "bar", "foo"])
expected_cache_output = [Generation(text="foo")]
cache_output = langchain.llm_cache.lookup("bar", llm_string)
assert cache_output == expected_cache_output
langchain.llm_cache = None
expected_generations = [
[Generation(text="fizz")],
[Generation(text="foo")],
[Generation(text="fizz")],
]
expected_output = LLMResult(
generations=expected_generations,
llm_output=None,
)
assert output == expected_output
_ = llm.generate(["foo", "bar", "foo"])
cache_output = langchain.llm_cache.lookup("foo", llm_string)
assert cache_output == [Generation(text="fizz")]
langchain.llm_cache.clear()
assert langchain.llm_cache.lookup("bar", llm_string) is None