镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-06 06:26:47 +00:00
update version 3.8
这个提交包含在:
@@ -1,17 +1,17 @@
|
||||
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
|
||||
from request_llms.bridge_all import model_info
|
||||
import random
|
||||
from functools import lru_cache
|
||||
from check_proxy import check_proxy
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from .prompts.Internet_GPT import Search_optimizer, Search_academic_optimizer
|
||||
import time
|
||||
import re
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from functools import lru_cache
|
||||
from itertools import zip_longest
|
||||
from check_proxy import check_proxy
|
||||
from toolbox import CatchException, update_ui, get_conf
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
from request_llms.bridge_all import model_info
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.prompts.internet import SearchOptimizerPrompt, SearchAcademicOptimizerPrompt
|
||||
|
||||
def search_optimizer(
|
||||
query,
|
||||
@@ -36,15 +36,15 @@ def search_optimizer(
|
||||
else:
|
||||
his += f"A: {h}\n"
|
||||
if categories == "general":
|
||||
sys_prompt = Search_optimizer.format(query=query, history=his, num=4)
|
||||
sys_prompt = SearchOptimizerPrompt.format(query=query, history=his, num=4)
|
||||
elif categories == "science":
|
||||
sys_prompt = Search_academic_optimizer.format(query=query, history=his, num=4)
|
||||
sys_prompt = SearchAcademicOptimizerPrompt.format(query=query, history=his, num=4)
|
||||
else:
|
||||
his = " "
|
||||
if categories == "general":
|
||||
sys_prompt = Search_optimizer.format(query=query, history=his, num=3)
|
||||
sys_prompt = SearchOptimizerPrompt.format(query=query, history=his, num=3)
|
||||
elif categories == "science":
|
||||
sys_prompt = Search_academic_optimizer.format(query=query, history=his, num=3)
|
||||
sys_prompt = SearchAcademicOptimizerPrompt.format(query=query, history=his, num=3)
|
||||
|
||||
mutable = ["", time.time(), ""]
|
||||
llm_kwargs["temperature"] = 0.8
|
||||
@@ -104,6 +104,7 @@ def search_optimizer(
|
||||
result.append(item)
|
||||
return result
|
||||
|
||||
|
||||
@lru_cache
|
||||
def get_auth_ip():
|
||||
ip = check_proxy(None, return_ip=True)
|
||||
@@ -111,6 +112,7 @@ def get_auth_ip():
|
||||
return '114.114.114.' + str(random.randint(1, 10))
|
||||
return ip
|
||||
|
||||
|
||||
def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
|
||||
if searxng_url is None:
|
||||
url = get_conf("SEARXNG_URL")
|
||||
@@ -162,6 +164,7 @@ def searxng_request(query, proxies, categories='general', searxng_url=None, engi
|
||||
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
|
||||
|
||||
@@ -189,6 +192,7 @@ def scrape_text(url, proxies) -> str:
|
||||
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, user_request):
|
||||
optimizer_history = history[:-8]
|
||||
@@ -202,8 +206,8 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
categories = plugin_kwargs.get('categories', 'general')
|
||||
searxng_url = plugin_kwargs.get('searxng_url', None)
|
||||
engines = plugin_kwargs.get('engine', None)
|
||||
optimizer = plugin_kwargs.get('optimizer', 0)
|
||||
if optimizer == 0:
|
||||
optimizer = plugin_kwargs.get('optimizer', "关闭")
|
||||
if optimizer == "关闭":
|
||||
urls = searxng_request(txt, proxies, categories, searxng_url, engines=engines)
|
||||
else:
|
||||
urls = search_optimizer(txt, proxies, optimizer_history, llm_kwargs, optimizer, categories, searxng_url, engines)
|
||||
@@ -216,7 +220,7 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
|
||||
# ------------- < 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
|
||||
if optimizer == 2:
|
||||
if optimizer == "开启(增强)":
|
||||
max_search_result = 8
|
||||
chatbot.append(["联网检索中 ...", None])
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
@@ -228,7 +232,7 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第3步:ChatGPT综合 > -------------
|
||||
if (optimizer == 0 or optimizer == 1):
|
||||
if (optimizer != "开启(增强)"):
|
||||
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,
|
||||
@@ -243,6 +247,7 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
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
|
||||
|
||||
#* 或者使用搜索优化器,这样可以保证后续问答能读取到有效的历史记录
|
||||
else:
|
||||
i_say = f"从以上搜索结果中抽取与问题:{txt} 相关的信息:"
|
||||
|
||||
@@ -26,7 +26,7 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
||||
"categories":
|
||||
ArgProperty(title="搜索分类", options=["网页", "学术论文"], default_value="网页", description="无", type="dropdown").model_dump_json(),
|
||||
"engine":
|
||||
ArgProperty(title="选择搜索引擎", options=["Mixed", "bing", "google", "duckduckgo"], default_value="Mixed", description="无", type="dropdown").model_dump_json(),
|
||||
ArgProperty(title="选择搜索引擎", options=["Mixed", "bing", "google", "duckduckgo"], default_value="google", description="无", type="dropdown").model_dump_json(),
|
||||
"optimizer":
|
||||
ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
|
||||
"searxng_url":
|
||||
@@ -41,7 +41,5 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
||||
"""
|
||||
if plugin_kwargs["categories"] == "网页": plugin_kwargs["categories"] = "general"
|
||||
if plugin_kwargs["categories"] == "学术论文": plugin_kwargs["categories"] = "science"
|
||||
optimizer_options=["关闭", "开启", "开启(增强)"]
|
||||
plugin_kwargs["optimizer"] = optimizer_options.index(plugin_kwargs["optimizer"])
|
||||
yield from 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
Search_optimizer="""作为一个网页搜索助手,你的任务是结合历史记录,从不同角度,为“原问题”生成个不同版本的“检索词”,从而提高网页检索的精度。生成的问题要求指向对象清晰明确,并与“原问题语言相同”。例如:
|
||||
SearchOptimizerPrompt="""作为一个网页搜索助手,你的任务是结合历史记录,从不同角度,为“原问题”生成个不同版本的“检索词”,从而提高网页检索的精度。生成的问题要求指向对象清晰明确,并与“原问题语言相同”。例如:
|
||||
历史记录:
|
||||
"
|
||||
Q: 对话背景。
|
||||
@@ -42,7 +42,7 @@ A: 1. Java 是一种编译型语言。
|
||||
直接给出最多{num}个检索词,必须以json形式给出,不得有多余字符:
|
||||
"""
|
||||
|
||||
Search_academic_optimizer="""作为一个学术论文搜索助手,你的任务是结合历史记录,从不同角度,为“原问题”生成个不同版本的“检索词”,从而提高学术论文检索的精度。生成的问题要求指向对象清晰明确,并与“原问题语言相同”。例如:
|
||||
SearchAcademicOptimizerPrompt="""作为一个学术论文搜索助手,你的任务是结合历史记录,从不同角度,为“原问题”生成个不同版本的“检索词”,从而提高学术论文检索的精度。生成的问题要求指向对象清晰明确,并与“原问题语言相同”。例如:
|
||||
历史记录:
|
||||
"
|
||||
Q: 对话背景。
|
||||
在新工单中引用
屏蔽一个用户