你好美丽的人！
我目前正试图在OpenAI的帮助下编写自己的“AI”。我遵循Langchain并设法最终得到了以下代码：

import os
import re

import discord
import requests
from discord.ext import commands
from langchain.chains import ConversationalRetrievalChain
from langchain.embeddings import OpenAIEmbeddings
from langchain.llms import OpenAI
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from transformers import GPT2TokenizerFast

intents = discord.Intents.default()
intents.typing = False
intents.presences = False
intents.message_content = True

bot = commands.Bot(command_prefix="!", intents=intents)

# Set up OpenAI API key and models
os.environ["OPENAI_API_KEY"] = 'xxxxxx'

def get_documentation():
    zendesk_url = "https://test.zendesk.com/api/v2/help_center/articles.json"

    documentation = []

    while zendesk_url:
        # Make a GET request to the Zendesk API to fetch articles for the current page
        response = requests.get(
            zendesk_url,
            headers={
                "Authorization": f"Basic xxxx",
                "Content-Type": "application/json"
            })

        # Check if the request was successful
        if response.status_code == 200:
            response_json = response.json()
            # Loop through the articles on the current page
            for article in response_json["articles"]:
                # Extract the title and body of the article
                title = article['title']
                body = article['body']

                # Remove any HTML tags and formatting from the body
                body = re.sub('<[^<]+?>', '', body)

                # Remove all newline characters from the body
                body = body.replace('\n', ' ')

                # Replace non-breaking spaces with regular spaces
                body = body.replace('\xa0', ' ')

                # Append the title and body to the documentation list
                documentation.append((title, body))

            # Check if there are more pages of articles and update the zendesk_url variable if necessary
            next_page_url = response_json["next_page"]
            zendesk_url = next_page_url if next_page_url else None
        else:
            # If the request was not successful, raise an exception with the error message
            response.raise_for_status()

    return documentation

# Load the GPT2 tokenizer
tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
print(tokenizer)

# Define a function to count tokens
def count_tokens(text: str) -> int:
    return len(tokenizer.encode(text))

# Create a text splitter
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=512,
    chunk_overlap=24,
    length_function=count_tokens,
)

# Fetch and clean the documentation
documentation = get_documentation() # The len of documentation is 93

# Extract only the article bodies
article_bodies = [article_body for title, article_body in documentation]

# Split the article bodies into chunks
chunks = text_splitter.create_documents(article_bodies)

# Get embedding model
embeddings = OpenAIEmbeddings()

# Create vector database
db = FAISS.from_documents(chunks, embeddings)

qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0.1), db.as_retriever())

@bot.event
async def on_ready():
    print(f'We have logged in as {bot.user}')

chat_history = []
@bot.command()
async def ask(ctx, *, question):
    print(f"{ctx.author.name} asked: {question}")
    result = qa(
        {
            "question": question,
            "chat_history": chat_history
        }
    )
    chat_history.append((question, result['answer']))
    await ctx.send(result['answer'])

bot.run('xxxxxx')

字符串
我所做的是连接到我的zendesk，通过调用get_documentation（）来抓取所有文档，然后使用它进行块。当我打电话！在这里提问，我应该得到答案。查看我的最新使用情况。它最终使用了大量的令牌，我觉得它可能太多了，可能需要一些解释，或者如果有什么我甚至可以改进？
x1c 0d1x的数据
我知道当我开始写脚本时，通常会有大约46,179个提示，但我真的不明白为什么我甚至没有开始问问题就付钱了。我如何改进它以使用更少的令牌？
预期：
使用较少的令牌/在我询问提示时使用令牌
实际：
每次启动时使用40 k+令牌。