Semantic Cache is not working #651
Description
I am utilizing the GPT Semantic Cache as outlined in the Langchain documentation, combined with the Groq API and the Llama3-70b-8192 model. However, I'm encountering an issue where the semantic cache returns the same response repeatedly, even when different questions are asked.
Can anybody know what could be the possible cause?
Here is the code:
import hashlib
from gptcache import Cache
from gptcache.adapter.api import init_similar_cache
from langchain.cache import GPTCache
from langchain_core.globals import set_llm_cache
def get_hashed_name(name):
return hashlib.sha256(name.encode()).hexdigest()
def init_gptcache(cache_obj: Cache, llm: str):
hashed_llm = get_hashed_name(llm)
init_similar_cache(cache_obj=cache_obj, data_dir=f"similar_cache_{hashed_llm}")
set_llm_cache(GPTCache(init_gptcache))