OpenAI 和 Apify - 似乎没有使用聊天机器人中存储的数据

Question

我一直在尝试使用 this 示例来构建一个 Python AI 聊天机器人，该机器人会抓取一个网站；存储数据并使用 OpenAI。

现在，我有 scrape.py，它获取存储在 .env 文件中的网站并将其保存到 Apify 中。这按预期工作并且数据存在。代码如下：

scrape.py

import os

from apify_client import ApifyClient
from dotenv import load_dotenv
from langchain_community.document_loaders import ApifyDatasetLoader
from langchain_community.document_loaders.base import Document
from langchain_community.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma

# Load environment variables from a .env file
load_dotenv()

if __name__ == '__main__':
    apify_client = ApifyClient(os.environ.get('APIFY_API_TOKEN'))
    website_url = os.environ.get('WEBSITE_URL')
    print(f'Extracting data from "{website_url}". Please wait...')
    actor_run_info = apify_client.actor('apify/website-content-crawler').call(
        run_input={'startUrls': [{'url': website_url}]}
    )
    print('Saving data into the vector database. Please wait...')
    loader = ApifyDatasetLoader(
        dataset_id=actor_run_info['defaultDatasetId'],
        dataset_mapping_function=lambda item: Document(
            page_content=item['text'] or '', metadata={'source': item['url']}
        ),
    )
    documents = loader.load()
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=100)
    docs = text_splitter.split_documents(documents)

    embedding = OpenAIEmbeddings()

    vectordb = Chroma.from_documents(
        documents=docs,
        embedding=embedding,
        persist_directory='db2',
    )
    vectordb.persist()
    print('All done!')

接下来，我们有 chat.py，它使用流打开聊天机器人，并询问有关 .env 文件中的网站的问题。我当前遇到的问题是聊天机器人可以工作，但是当我问诸如“开放时间是多少”之类的问题时，它似乎没有使用存储的数据，而是试图浏览互联网，它会说“我”抱歉，我无法获取实时信息或浏览互联网。'

我不确定这是为什么，并且似乎无法在网上找到更多信息。任何帮助或指导都会令人难以置信！

聊天.py

import os

import streamlit as st
from dotenv import load_dotenv
from langchain.callbacks.base import BaseCallbackHandler
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.memory import ConversationBufferMemory
from langchain.memory.chat_message_histories import StreamlitChatMessageHistory
from langchain.vectorstores import Chroma

load_dotenv()

website_url = os.environ.get('WEBSITE_URL', 'a website')

st.set_page_config(page_title=f'Chat with {website_url}')
st.title('Learn about Alnwick gardens')

@st.cache_resource(ttl='1h')
def get_retriever():
    embeddings = OpenAIEmbeddings()
    vectordb = Chroma(persist_directory='db', embedding_function=embeddings)

    retriever = vectordb.as_retriever(search_type='mmr')

    return retriever

class StreamHandler(BaseCallbackHandler):
    def __init__(self, container: st.delta_generator.DeltaGenerator, initial_text: str = ''):
        self.container = container
        self.text = initial_text

    def on_llm_new_token(self, token: str, **kwargs) -> None:
        self.text += token
        self.container.markdown(self.text)

retriever = get_retriever()

msgs = StreamlitChatMessageHistory()
memory = ConversationBufferMemory(memory_key='chat_history', chat_memory=msgs, return_messages=True)

llm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0, streaming=True)
qa_chain = ConversationalRetrievalChain.from_llm(
    llm, retriever=retriever, memory=memory, verbose=False
)

if st.sidebar.button('Clear message history') or len(msgs.messages) == 0:
    msgs.clear()
    msgs.add_ai_message(f'Ask me anything about {website_url}!')

avatars = {'human': 'user', 'ai': 'assistant'}
for msg in msgs.messages:
    st.chat_message(avatars[msg.type]).write(msg.content)

if user_query := st.chat_input(placeholder='Ask me anything!'):
    st.chat_message('user').write(user_query)

    with st.chat_message('assistant'):
        stream_handler = StreamHandler(st.empty())
        response = qa_chain.run(user_query, callbacks=[stream_handler])

Answer 1

修好了。原来只是调用了错误的数据库

persist_directory='db2'

被设置为抓取但未在聊天中调用！