GPT Cache：1 介绍

towhee = Towhee(model="uer/albert-base-chinese-cluecorpussmall")

pip install gptcache

from gptcache.core import cache
cache.init()
# 如果使用`openai.api_key = xxx`设置API KEY，需要用下面语句替换它
# 方法读取OPENAI_API_KEY环境变量并进行设置，保证key的安全性 
cache.set_openai_key()

from gptcache.core import cache

# openai请求不需要做任何改变
answer = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "foo"}
        ],
    )

import json
import os
import time

from gptcache.cache.factory import get_data_manager, get_si_data_manager
from gptcache.core import cache, Cache
from gptcache.encoder import Towhee
from gptcache.ranker.simple import pair_evaluation
from gptcache.adapter import openai


def run():
    towhee = Towhee()
    # towhee = Towhee(model="uer/albert-base-chinese-cluecorpussmall")
    
    os.environ["OPENAI_API_KEY"] = "API KEY"
    cache.set_openai_key()

    data_manager = get_si_data_manager("sqlite", "faiss",
                                       dimension=towhee.dimension(), max_size=2000)
    cache.init(embedding_func=towhee.to_embeddings,
               data_manager=data_manager,
               evaluation_func=pair_evaluation,
               similarity_threshold=1,
               similarity_positive=False)

    question1 = "what do you think about GPT"
    question2 = "what do you feel like GPT"

    # question1 = "做博后有什么优势？"
    # question2 = "为什么有人会选择做博后？"

    start_time = time.time()
    answer = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "user", "content": question1}
        ],
    )
    end_time = time.time()
    print("time consuming: {:.2f}s".format(end_time - start_time))
    print(json.dumps(answer))

    start_time = time.time()
    answer = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "user", "content": question2}
        ],
    )
    end_time = time.time()
    print("time consuming: {:.2f}s".format(end_time - start_time))

    print(answer)


if __name__ == '__main__':
    run()

time consuming: 12.83s
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "As an AI language model, I do not have personal opinions or biases towards websites or specific platforms. However, I can say that GPT is a platform designed for interactive communication where users can connect with others and have conversations on various topics such as lifestyle, relationships, health, and personal growth among others. It could be a useful tool for individuals seeking support or advice from peers, or just for casual conversations to pass the time.",
        "role": "assistant"
      }
    }
  ],
  "created": 1680272771,
  "id": "chatcmpl-709zfmJyYDEl4dfTFfmAlfq7luTjM",
  "model": "gpt-3.5-turbo-0301",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 87,
    "prompt_tokens": 16,
    "total_tokens": 103
  }
}
time consuming: 0.06s
{'gpt_cache': True, 'choices': [{'message': {'role': 'assistant', 'content': 'As an AI language model, I do not have personal opinions or biases towards websites or specific platforms. However, I can say that GPT is a platform designed for interactive communication where users can connect with others and have conversations on various topics such as lifestyle, relationships, health, and personal growth among others. It could be a useful tool for individuals seeking support or advice from peers, or just for casual conversations to pass the time.'}, 'finish_reason': 'stop', 'index': 0}]}