【单元测试】添加联网回答问题的功能
This commit is contained in:
parent
b42f2f745f
commit
bff4a87914
@ -79,14 +79,23 @@ def test_下载arxiv论文并翻译摘要():
|
||||
for cookies, cb, hist, msg in 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
print(cb)
|
||||
|
||||
test_解析一个Python项目()
|
||||
test_Latex英文润色()
|
||||
test_Markdown中译英()
|
||||
test_批量翻译PDF文档()
|
||||
test_谷歌检索小助手()
|
||||
test_总结word文档()
|
||||
test_下载arxiv论文并翻译摘要()
|
||||
test_解析一个Cpp项目()
|
||||
def test_联网回答问题():
|
||||
from crazy_functions.联网的ChatGPT import 连接网络回答问题
|
||||
txt = "“我们称之为高效”是什么梗?"
|
||||
for cookies, cb, hist, msg in 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
print(cb)
|
||||
|
||||
# test_解析一个Python项目()
|
||||
# test_Latex英文润色()
|
||||
# test_Markdown中译英()
|
||||
# test_批量翻译PDF文档()
|
||||
# test_谷歌检索小助手()
|
||||
# test_总结word文档()
|
||||
# test_下载arxiv论文并翻译摘要()
|
||||
# test_解析一个Cpp项目()
|
||||
|
||||
test_联网回答问题()
|
||||
|
||||
|
||||
input("程序完成,回车退出。")
|
||||
print("退出。")
|
91
crazy_functions/联网的ChatGPT.py
Normal file
91
crazy_functions/联网的ChatGPT.py
Normal file
@ -0,0 +1,91 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from request_llm.bridge_all import model_info
|
||||
|
||||
def google(query, proxies):
|
||||
query = query # 在此处替换您要搜索的关键词
|
||||
url = f"https://www.google.com/search?q={query}"
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'}
|
||||
response = requests.get(url, headers=headers, proxies=proxies)
|
||||
soup = BeautifulSoup(response.content, 'html.parser')
|
||||
results = []
|
||||
for g in soup.find_all('div', class_='g'):
|
||||
anchors = g.find_all('a')
|
||||
if anchors:
|
||||
link = anchors[0]['href']
|
||||
if link.startswith('/url?q='):
|
||||
link = link[7:]
|
||||
if not link.startswith('http'):
|
||||
continue
|
||||
title = g.find('h3').text
|
||||
item = {'title': title, 'link': link}
|
||||
results.append(item)
|
||||
|
||||
for r in results:
|
||||
print(r['link'])
|
||||
return results
|
||||
|
||||
def scrape_text(url, proxies) -> str:
|
||||
"""Scrape text from a webpage
|
||||
|
||||
Args:
|
||||
url (str): The URL to scrape text from
|
||||
|
||||
Returns:
|
||||
str: The scraped text
|
||||
"""
|
||||
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'}
|
||||
response = requests.get(url, headers=headers, proxies=proxies)
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
for script in soup(["script", "style"]):
|
||||
script.extract()
|
||||
text = soup.get_text()
|
||||
lines = (line.strip() for line in text.splitlines())
|
||||
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
|
||||
text = "\n".join(chunk for chunk in chunks if chunk)
|
||||
return text
|
||||
|
||||
@CatchException
|
||||
def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
"""
|
||||
txt 输入栏用户输入的文本,例如需要翻译的一段话,再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数,如温度和top_p等,一般原样传递下去就行
|
||||
plugin_kwargs 插件模型的参数,暂时没有用武之地
|
||||
chatbot 聊天显示框的句柄,用于显示给用户
|
||||
history 聊天历史,前情提要
|
||||
system_prompt 给gpt的静默提醒
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
history = [] # 清空历史,以免输入溢出
|
||||
chatbot.append((f"请结合互联网信息回答以下问题:{txt}",
|
||||
"[Local Message] 请注意,您正在调用一个[函数插件]的模板,该模板可以实现ChatGPT联网信息综合。该函数面向希望实现更多有趣功能的开发者,它可以作为创建新功能函数的模板。您若希望分享新的功能模组,请不吝PR!"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间,我们先及时地做一次界面更新
|
||||
|
||||
# ------------- < 第1步:爬取搜索引擎的结果 > -------------
|
||||
from toolbox import get_conf
|
||||
proxies, = get_conf('proxies')
|
||||
urls = google(txt, proxies)
|
||||
history = []
|
||||
|
||||
# ------------- < 第2步:依次访问网页 > -------------
|
||||
max_search_result = 5
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
res = scrape_text(url['link'], proxies)
|
||||
history.extend([f"第{index}份搜索结果", res])
|
||||
chatbot.append([f"第{index}份搜索结果", res])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间,我们先及时地做一次界面更新
|
||||
|
||||
# ------------- < 第3步:综合 > -------------
|
||||
i_say = f"从以上搜索结果中抽取信息,然后回答问题:{txt}"
|
||||
i_say, history = input_clipping(inputs=i_say, history=history, max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']//2)
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt="请从给定文本中抽取信息"
|
||||
)
|
||||
chatbot[-1] = (i_say, gpt_say)
|
||||
history.append(i_say);history.append(gpt_say)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
Loading…
x
Reference in New Issue
Block a user