GPTCache:为 LLM 查询创建语义缓存的库

bluesky10月前 ⋅ 908 阅读

https://github.com/zilliztech/GPTCache

将您的 LLM API 成本削减 10 倍💰, 将速度提高 100 倍

// OpenAI API + GPTCache,使用温度

import time

from gptcache import cache, Config
from gptcache.manager import manager_factory
from gptcache.embedding import Onnx
from gptcache.processor.post import temperature_softmax
from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation
from gptcache.adapter import openai

cache.set_openai_key()

onnx = Onnx()
data_manager = manager_factory("sqlite,faiss", vector_params={"dimension": onnx.dimension})

cache.init(
    embedding_func=onnx.to_embeddings,
    data_manager=data_manager,
    similarity_evaluation=SearchDistanceEvaluation(),
    post_process_messages_func=temperature_softmax
    )
# cache.config = Config(similarity_threshold=0.2)

question = "what's github"

for _ in range(3):
    start = time.time()
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        temperature = 1.0,  # Change temperature here
        messages=[{
            "role": "user",
            "content": question
        }],
    )
    print("Time elapsed:", round(time.time() - start, 3))
    print("Answer:", response["choices"][0]["message"]["content"])

全部评论: 0

    相关推荐