镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-06 06:26:47 +00:00
internet GPT upgrade
这个提交包含在:
@@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from toolbox import CatchException, update_ui, get_conf
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
@@ -6,7 +6,6 @@ from request_llms.bridge_all import model_info
|
||||
import urllib.request
|
||||
from functools import lru_cache
|
||||
|
||||
|
||||
@lru_cache
|
||||
def get_auth_ip():
|
||||
try:
|
||||
@@ -15,12 +14,16 @@ def get_auth_ip():
|
||||
except:
|
||||
return '114.114.114.114'
|
||||
|
||||
def searxng_request(query, proxies):
|
||||
url = 'https://cloud-1.agent-matrix.com/' # 请替换为实际的API URL
|
||||
def searxng_request(query, proxies, categories='general', searxng_url=None):
|
||||
if searxng_url is None:
|
||||
url = get_conf("SEARXNG_URL")
|
||||
else:
|
||||
url = searxng_url
|
||||
params = {
|
||||
'q': query, # 搜索查询
|
||||
'format': 'json', # 输出格式为JSON
|
||||
'language': 'zh', # 搜索语言
|
||||
'categories': categories
|
||||
}
|
||||
headers = {
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9',
|
||||
@@ -41,7 +44,10 @@ def searxng_request(query, proxies):
|
||||
results.append(item)
|
||||
return results
|
||||
else:
|
||||
raise ValueError("搜索失败,状态码: " + str(response.status_code) + '\t' + response.content.decode('utf-8'))
|
||||
if response.status_code == 429:
|
||||
raise ValueError("Searxng(在线搜索服务)当前使用人数太多,请稍后。")
|
||||
else:
|
||||
raise ValueError("在线搜索失败,状态码: " + str(response.status_code) + '\t' + response.content.decode('utf-8'))
|
||||
|
||||
def scrape_text(url, proxies) -> str:
|
||||
"""Scrape text from a webpage
|
||||
@@ -72,29 +78,23 @@ def scrape_text(url, proxies) -> str:
|
||||
|
||||
@CatchException
|
||||
def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
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
|
||||
user_request 当前用户的请求信息(IP地址等)
|
||||
"""
|
||||
|
||||
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
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第1步:爬取搜索引擎的结果 > -------------
|
||||
from toolbox import get_conf
|
||||
proxies = get_conf('proxies')
|
||||
urls = searxng_request(txt, proxies)
|
||||
categories = plugin_kwargs.get('categories', 'general')
|
||||
searxng_url = plugin_kwargs.get('searxng_url', None)
|
||||
urls = searxng_request(txt, proxies, categories, searxng_url)
|
||||
history = []
|
||||
if len(urls) == 0:
|
||||
chatbot.append((f"结论:{txt}",
|
||||
"[Local Message] 受到google限制,无法从google获取信息!"))
|
||||
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
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
# ------------- < 第2步:依次访问网页 > -------------
|
||||
max_search_result = 5 # 最多收纳多少个网页的结果
|
||||
@@ -102,14 +102,14 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
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[:500]+"......"])
|
||||
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
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第3步:ChatGPT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( # 裁剪输入,从最长的条目开始裁剪,防止爆token
|
||||
inputs=i_say,
|
||||
history=history,
|
||||
max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
|
||||
max_token_limit=min(model_info[llm_kwargs['llm_model']]['max_token']*3//4, 8192)
|
||||
)
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
|
||||
在新工单中引用
屏蔽一个用户