requirements.txt

Flask==2.2.3
Flask-Cors==3.0.10
langchain==0.0.115
llama-index==0.4.30
PyPDF2==3.0.1

index_server.py

import os
import pickle
# 這里可以換成你自己的key，但是最好不要上傳到github上
os.environ['OPENAI_API_KEY'] = ""
from multiprocessing import Lock
from multiprocessing.managers import BaseManager
from llama_index import SimpleDirectoryReader, GPTSimpleVectorIndex, Document
index = None
stored_docs = {}
lock = Lock()
# 保存index的json文件
index_name = "./index.json"
# 保存文檔的pkl文件 用于保存文檔的id和文本，這樣客戶端就可以查詢到文檔的列表了
pkl_name = "stored_documents.pkl"
def initialize_index():
    """初始化index，如果已經(jīng)存在index，就使用已經(jīng)訓(xùn)練好的index，否則就創(chuàng)建一個新的index"""
    global index, stored_docs
    with lock:
        if os.path.exists(index_name):
            """使用已經(jīng)訓(xùn)練好的index"""
            index = GPTSimpleVectorIndex.load_from_disk(index_name)
        else:
            """使用GPTSimpleVectorIndex創(chuàng)建一個新的index 這里是llama_index的一個bug，如果你不傳入一個空的list，就會報錯 """
            index = GPTSimpleVectorIndex([])
            index.save_to_disk(index_name)
        if os.path.exists(pkl_name):
            with open(pkl_name, "rb") as f:
                stored_docs = pickle.load(f)
def query_index(query_text):
    """查詢index 根據(jù)你查詢的文本，返回一個response"""
    global index
    response = index.query(query_text)
    return response
def insert_into_index(doc_file_path, doc_id=None):
    """將文檔插入到index中，插入的文檔可以是一個文件，也可以是一個字符串，
    如果doc_id不為空，就使用doc_id，否則就使用文件名作為doc_id"""
    global index, stored_docs
    document = SimpleDirectoryReader(input_files=[doc_file_path]).load_data()[0]
    if doc_id is not None:
        document.doc_id = doc_id
    # Keep track of stored docs -- llama_index doesn't make this easy
    stored_docs[document.doc_id] = document.text[0:200]  # only take the first 200 chars
    with lock:
        index.insert(document)
        index.save_to_disk(index_name)
        with open(pkl_name, "wb") as f:
            pickle.dump(stored_docs, f)
    return
def get_documents_list():
    """查詢保存的文檔列表，返回一個list"""
    global stored_doc
    documents_list = []
    for doc_id, doc_text in stored_docs.items():
        documents_list.append({"id": doc_id, "text": doc_text})
    return documents_list
if __name__ == "__main__":
    # 初始化index， 如果已經(jīng)存在index，就使用已經(jīng)訓(xùn)練好的index，否則就創(chuàng)建一個新的index
    print("initializing index...")
    initialize_index()
    # 啟動服務(wù)器，監(jiān)聽5602端口
    manager = BaseManager(('127.0.0.1', 5602), b'123456')
    # 注冊使用到的函數(shù)，這樣客戶端就可以調(diào)用這些函數(shù)了
    manager.register('query_index', query_index)
    manager.register('insert_into_index', insert_into_index)
    manager.register('get_documents_list', get_documents_list)
    server = manager.get_server()
    print("server started...")
    server.serve_forever()

$ python index_server.py
initializing index...
server started...