goldfishh/chatgpt-tool-hub

An open-source chatgpt tool ecosystem where you can combine tools with chatgpt and use natural language to do anything.

👋 Hello! I'm goldfish, aka `goldfis[h]+`

• 📍 I’m currently working at Alibaba DAMO Academy.
• 🌱 I’m an algorithm engineer, focusing on the engineering implementation of visual algorithms.
• 💬 I enjoy programming and am particularly interested in projects that use LLM (Large Language Models).
• ⌨️ I can use C++, Python, Java, and Go to implement ideas.
• 💡 How to reach me: Zhihu • Bilibili
• 😼 Fun fact: like white-haired catgirl

---

🔧 Recent Activity

🐱 My GitHub Data

📦 33.8 kB Used in GitHub's Storage

🏆 170 Contributions in the Year 2024

🚫 Not Opted to Hire

📜 22 Public Repositories

🔑 6 Private Repositories

I'm an Early 🐤

🌞 Morning                419 commits         ███████████████░░░░░░░░░░   59.10 % 
🌆 Daytime                24 commits          █░░░░░░░░░░░░░░░░░░░░░░░░   03.39 % 
🌃 Evening                147 commits         █████░░░░░░░░░░░░░░░░░░░░   20.73 % 
🌙 Night                  119 commits         ████░░░░░░░░░░░░░░░░░░░░░   16.78 % 

📅 I'm Most Productive on Thursday

Monday                   98 commits          ███░░░░░░░░░░░░░░░░░░░░░░   13.82 % 
Tuesday                  83 commits          ███░░░░░░░░░░░░░░░░░░░░░░   11.71 % 
Wednesday                117 commits         ████░░░░░░░░░░░░░░░░░░░░░   16.50 % 
Thursday                 136 commits         █████░░░░░░░░░░░░░░░░░░░░   19.18 % 
Friday                   81 commits          ███░░░░░░░░░░░░░░░░░░░░░░   11.42 % 
Saturday                 88 commits          ███░░░░░░░░░░░░░░░░░░░░░░   12.41 % 
Sunday                   106 commits         ████░░░░░░░░░░░░░░░░░░░░░   14.95 % 

📊 This Week I Spent My Time On

🕑︎ Time Zone: Asia/Shanghai

💬 Programming Languages: 
Python                   46 mins             █████████████████░░░░░░░░   68.36 % 
C++                      9 mins              ████░░░░░░░░░░░░░░░░░░░░░   14.46 % 
JSON                     5 mins              ██░░░░░░░░░░░░░░░░░░░░░░░   07.47 % 
CMake                    2 mins              █░░░░░░░░░░░░░░░░░░░░░░░░   03.42 % 
Other                    1 min               █░░░░░░░░░░░░░░░░░░░░░░░░   02.75 % 

💻 Operating System: 
Mac                      1 hr 8 mins         █████████████████████████   100.00 % 

Last Updated on 02/06/2024 01:17:44 UTC

---

📆 Github Stats

---

📊 Visit Count

chatgpt-tool-hub's Issues

新闻类的工具调用不是很准确

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

已拉取更新最新代码，依赖
chatgpt-on-wechat版本：1.2.5
chatgpt-tool-hub版本：0.4.3

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [
    "news",
    "arxiv",
    "debug",
    "summary",
    "url-get",
    "terminal",
    "wikipedia",
    "bing-search",
    "meteo-weather",
    "wolfram-alpha"

  ],
  "kwargs": {
    "top_k_results": 2,
    "no_default": true,
    "debug": true,
    "searx_host": "",
    "model_name": "gpt-3.5-turbo",
    "bing_subscription_key": "278fc47d0cd218",
    "news_api_key":"f2fddd62b941",
    "wolfram_alpha_appid":"7UH8R7RJ4H",
    "google_api_key": "vhrasGFEwAkp3Fm1-Mg",
    "google_cse_id": "dc84eb3",
    "zaobao_api_key": "8Qwk"
  }
}

2. 你的问题：

无论怎么引导，它却只调用news-api，而不调用morning-news
或者还是说我询问的方式不对？

3. 收到ai的回复：
   
   

4. debug模式终端打印的日志：
   

环境

• 操作系统类型 Linux：Ubuntu-22.04-x64
• Python版本：3.10
• pip版本 pip -V：22.0.2

morningnews和wolfram-alpha插件添加报错

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

还有morningnews也是添加不了的

早报获取失败 超过重试次数

[INFO][2023-04-12 10:26:34][base.py:109] - 执行Tool: news中...
[INFO][2023-04-12 10:26:34][bot.py:87] - 行动输入: 给我今天的早报
[ERROR][2023-04-12 10:26:39][victorinox.py:86] - [APP] catch a Exception: Invalid URL 'Sorry, the API documentation is missing. Without the API documentation, I cannot generate the full API URL to answer the user question. Please provide the API documentation.': No scheme supplied. Perhaps you meant https://Sorry, the API documentation is missing. Without the API documentation, I cannot generate the full API URL to answer the user question. Please provide the API documentation.?
[INFO][2023-04-12 10:26:43][base.py:109] - 执行Tool: news中...
[INFO][2023-04-12 10:26:43][bot.py:87] - 行动输入: 给我今天的早报
[ERROR][2023-04-12 10:26:47][victorinox.py:86] - [APP] catch a Exception: Invalid URL 'Sorry, the API documentation is missing. Please provide the necessary information to generate the API url.': No scheme supplied. Perhaps you meant https://Sorry, the API documentation is missing. Please provide the necessary information to generate the API url.?
[ERROR][2023-04-12 10:26:47][victorinox.py:90] - exceed retry_num
[ERROR][2023-04-12 10:26:47][tool.py:92] - 超过重试次数
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 84, in ask
return self.bot.run(query)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 156, in _call
next_step_output = self._take_next_step(
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 122, in _take_next_step
observation = tool.run(
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 73, in run
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 70, in run
observation = self._run(tool_input)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/news/news.py", line 41, in _run
return self.api_chain.run(query)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/api/base.py", line 73, in _call
api_response = self.requests_wrapper.get(api_url)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/web_requests/wrapper.py", line 93, in get
response = requests.get(url, headers=self.headers, params=params, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/api.py", line 73, in get
return request("get", url, params=params, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/sessions.py", line 573, in request
prep = self.prepare_request(req)
File "/usr/local/lib/python3.10/dist-packages/requests/sessions.py", line 484, in prepare_request
p.prepare(
File "/usr/local/lib/python3.10/dist-packages/requests/models.py", line 368, in prepare
self.prepare_url(url, params)
File "/usr/local/lib/python3.10/dist-packages/requests/models.py", line 439, in prepare_url
raise MissingSchema(
requests.exceptions.MissingSchema: Invalid URL 'Sorry, the API documentation is missing. Without the API documentation, I cannot generate the full API URL to answer the user question. Please provide the API documentation.': No scheme supplied. Perhaps you meant https://Sorry, the API documentation is missing. Without the API documentation, I cannot generate the full API URL to answer the user question. Please provide the API documentation.?

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 84, in ask
return self.bot.run(query)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 156, in _call
next_step_output = self._take_next_step(
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 122, in _take_next_step
observation = tool.run(
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 73, in run
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 70, in run
observation = self._run(tool_input)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/news/news.py", line 41, in _run
return self.api_chain.run(query)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/chains/api/base.py", line 73, in _call
api_response = self.requests_wrapper.get(api_url)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/tools/web_requests/wrapper.py", line 93, in get
response = requests.get(url, headers=self.headers, params=params, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/api.py", line 73, in get
return request("get", url, params=params, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/requests/sessions.py", line 573, in request
prep = self.prepare_request(req)
File "/usr/local/lib/python3.10/dist-packages/requests/sessions.py", line 484, in prepare_request
p.prepare(
File "/usr/local/lib/python3.10/dist-packages/requests/models.py", line 368, in prepare
self.prepare_url(url, params)
File "/usr/local/lib/python3.10/dist-packages/requests/models.py", line 439, in prepare_url
raise MissingSchema(
requests.exceptions.MissingSchema: Invalid URL 'Sorry, the API documentation is missing. Please provide the necessary information to generate the API url.': No scheme supplied. Perhaps you meant https://Sorry, the API documentation is missing. Please provide the necessary information to generate the API url.?

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/chatgpt-on-wechat-1.2.1.2/plugins/tool/tool.py", line 88, in on_handle_context
_reply = self.app.ask(query, user_session)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 88, in ask
return self.ask(query, chat_history, retry_num + 1)
File "/usr/local/lib/python3.10/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 91, in ask
raise TimeoutError("超过重试次数")
TimeoutError: 超过重试次数
[ERROR][2023-04-12 10:26:47][tool.py:93] - 超过重试次数
[INFO][2023-04-12 10:26:47][chat_gpt_bot.py:36] - [CHATGPT] query=请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理
[INFO][2023-04-12 10:27:05][wechat_channel.py:174] - [WX] sendMsg=Reply(type=TEXT, content=[GPT] 嘿，你好啊！非常抱歉，我需要告诉你一件事。这个问题需要使用特定的工具插件来处理，而目前我的系统暂时没有这些插件。因此，我不能为您提供解决方案。但是别担心，我一直在快速学习和发展，希望不久的将来，我可以回答所有您的问题。非常感谢您的理解！), receiver=@45c666477c9b891bdfc3396a9547cf48cabd79e5d17e5650a31b03a69c980484

早报请求超时的问题

chatgpt-on-wechat版本：1.2.3
chatgpt-tool-hub版本：0.3.9

从昨天开始早报就一直请求超时，看了下接口调用日志是有返回内容的，是我哪里配置的不对吗？

---

[INFO][2023-04-13 15:03:29][bridge.py:28] - create bot chatGPT for chat
[INFO][2023-04-13 15:03:56][base.py:109] - 执行Tool: morning-news中...
[INFO][2023-04-13 15:03:56][bot.py:87] - 行动输入: 给我今天的早报
[WARNING][2023-04-13 15:04:57][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60).
[ERROR][2023-04-13 15:06:01][victorinox.py:86] - [APP] catch a Exception: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60)
[INFO][2023-04-13 15:06:36][base.py:109] - 执行Tool: morning-news中...
[INFO][2023-04-13 15:06:36][bot.py:87] - 行动输入: 给我今天的早报
[WARNING][2023-04-13 15:07:36][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60).
[ERROR][2023-04-13 15:08:41][victorinox.py:86] - [APP] catch a Exception: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60)
[ERROR][2023-04-13 15:08:41][victorinox.py:90] - exceed retry_num
[ERROR][2023-04-13 15:08:41][tool.py:92] - 超过重试次数

我是试着修改下面的配置，但还是没用
"request_timeout": 300,
"timeout": 300,

Meteo Weather需要设置APIkey么？天气查询失败

[INFO][2023-04-11 09:39:13][base.py:99] - 执行Tool: Meteo Weather中...
[INFO][2023-04-11 09:39:13][bot.py:87] - 行动输入: 查询沈阳4月11日的天气怎么样
[INFO][2023-04-11 09:39:51][bot.py:87] - 行动输入: 由于API密钥无效，我无法获取沈阳4月11日的天气信息。请提供有效的API密钥以获取天气信息。
[INFO][2023-04-11 09:39:53][wechat_channel.py:164] - [WX] sendMsg=Reply(type=TEXT, content=[bot]由于API密钥无效，我无法获取沈阳4月11日的天气信息。请提供有效的API密钥以获取天气信息。), receiver=@4d7df954e1085ea9dfb9ed45c772fce6

为什么news用不了

这是log
'''
已加载工具列表:
terminal, wikipedia, wolfram-alpha, url-get, meteo-weather, python), receiver=@c95520fffe8bxxxxxxxxxxx
[INFO][2023-05-15 19:24:27][init.py:29] - [visual_dl] init failed, error_info: ModuleNotFoundError("No module named 'torch'")
[WARNING][2023-05-15 19:24:27][tool.py:171] - [tool] filter invalid tool: 'news'
[WARNING][2023-05-15 19:24:27][tool.py:171] - [tool] filter invalid tool: 'morning-news'
[INFO][2023-05-15 19:24:27][init.py:29] - [visual_dl] init failed, error_info: ModuleNotFoundError("No module named 'torch'")
[WARNING][2023-05-15 19:24:27][victorinox.py:41] - refresh the config of tools
[WARNING][2023-05-15 19:24:27][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[INFO][2023-05-15 19:24:27][victorinox.py:86] - use_tools=['terminal', 'wikipedia', 'wolfram-alpha', 'url-get', 'meteo-weather', 'python'], params: {'debug': False, 'openai_api_key': 'sk-', 'open_ai_api_base': 'https://chatgp/v1', 'proxy': '', 'request_timeout': 120, 'model_name': 'gpt-3.5-turbo', 'no_default': False, 'top_k_results': 3, 'news_api_key': 'd650dxxxxxxxx069e0a', 'bing_subscription_key': '', 'google_api_key': '', 'google_cse_id': '', 'searx_search_host': '', 'wolfram_alpha_appid': '8EWxxxxxxxTXA', 'morning_news_api_key': 'N0VxxxxxxxxxxL0U', 'cuda_device': 'cpu', 'think_depth': 3, 'arxiv_summary': True, 'morning_news_use_llm': False}
[INFO][2023-05-15 19:24:27][wechat_channel.py:184] - [WX] sendMsg=Reply(type=TEXT, content=[bot] 重置工具成功), receiver=@c95520fffxxxxxxxxxxx
[INFO][2023-05-15 19:24:33][wechat_channel.py:187] - [WX] sendMsg=Reply(type=INFO, content=[INFO]
这是一个能让chatgpt联网，搜索，数字运算的插件，将赋予强大且丰富的扩展能力。
使用说明：
$tool 命令: 根据给出的{命令}使用一些可用工具尽力为你得到结果。
$tool reset: 重置工具。

已加载工具列表:
terminal, wikipedia, wolfram-alpha, url-get, meteo-weather, python), receiver=@c95520fffe8b2xxxxxxxxxxxxxxxxx
'''

多此一举地问一下，LLM-OS返回的结果可以再characterize一道吗（

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

/

2. 你的问题：

就是让$tool的回复也能role play

3. 收到ai的回复：

/

4. debug模式终端打印的日志：

/

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

LLM-OS 海外服务器连接超时

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

海外服务器未设置代理，LLM-OS好像是连接不上网络，需要设置代理吗？

1. 你复现时的config.json，注意抹去你的api-key

----config.json-----

{
  "tools": [
    "news",
    "arxiv",
    "debug",
    "summary",
    "url-get",
    "wikipedia",
    "bing-search",
    "meteo-weather",
    "wolfram-alpha"

  ],
  "kwargs": {
    "model_name": "gpt-3.5-turbo",
    "proxy": "",
    "searx_host": "",
    "top_k_results": 2,
    "no_default": true,
    "debug": true,
    "morning_news_use_llm": true,
    "arxiv_summary": false,
    "bing_subscription_key": " 8a278fc47d08",
    "news_api_key":"9698f2fddd62b941",
    "wolfram_alpha_appid":"R7RJ4H",
    "google_api_key": "FEwAkp3Fm1-Mg",
    "google_cse_id": "ddc84eb3",
    "morning_news_api_key": "8Qwk"
  }
}

---- .env -------

LLM_API_KEY=sk-xIszmyGxY
LLM_API_BASE_URL=
MODEL_NAME=
THINK_DEPTH=
REQUEST_TIMEOUT=
PROXY=
DEBUG=true

4. debug模式终端打印的日志：

root@ser074585755966:~# cd chatgpt-tool-hub
root@ser074585755966:~/chatgpt-tool-hub# python3 terminal_io.py
chatgpt-tool-hub version: 0.4.3
Debug 模式 已开启
user 你好 👋  欢迎进入 LLM-OS! 
输入 `/help` 可以获得帮助信息 
目前LLM-OS开发者只有我 能预见有大量🔧不能兼顾 请见谅 😣 
欢迎提issue和pr 希望这个项目变得更好 📈
> user: hello
错误: 超过重试次数. 
> user: 你好
错误: 超过重试次数. 

wechat项目上使用wolfram-alpha插件出错

已在config.json配置了appid 以及把wolfram-alpha包复制到到WeChat项目里

用url-get从谷歌或者其他搜索引擎下获得解码出现问题。

INFO][2023-04-19 10:50:51][base.py:107] - 执行Tool: url-get中...
[INFO][2023-04-19 10:50:51][bot.py:91] - 输入: https://www.google.com/search?q=%E4%B8%AD%E7%89%B9%E4%BC%B0
DEBUG][2023-04-19 10:50:53][tool_engine.py:139] - llm received: `"UnicodeEncodeError('gbk', '中特估 - Google 検索×数秒たってもリダイレクトされない場合は、ここをクリックしてください。\r\nすべてニュース画像動画 地図 ショッピング 書籍 検索ツール\r\nすべての言語すべての言語日本語のページを検索期間指定なし期間指定なし 1 時間以内 24 時間以内 1 週間以内 1 か月以内 1 年以内すべての結果すべての結果完全一致“中特估”是什么？ - 新浪财经finance.sina.com.cn › jjzl › doc-imymrxkr99179312023/03/21 · “中特估”主要以央企、国企以及一些特殊行业的上市公司为主

天气无法获取（内含日志）

在执行“使用meteo，告诉我今天广州天气”时出现问题，以下是日志

[INFO][2023-04-15 05:32:39][base.py:109] - 执行Tool: meteo-weather中...
[INFO][2023-04-15 05:32:39][bot.py:87] - 行动输入: 今天广州的天气 daily
[WARNING][2023-04-15 05:32:39][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-bP7cJd3Y9irUV7534hWo4ETp on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method..
[ERROR][2023-04-15 05:32:44][victorinox.py:86] - [APP] catch a Exception: Rate limit reached for default-gpt-3.5-turbo in organization org-bP7cJd3Y9irUV7534hWo4ETp on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.
[ERROR][2023-04-15 05:32:44][victorinox.py:90] - exceed retry_num
[ERROR][2023-04-15 05:32:44][tool.py:92] - 超过重试次数
Traceback (most recent call last):
File "/usr/lib/python3/dist-packages/urllib3/connection.py", line 159, in _new_conn
conn = connection.create_connection(
File "/usr/lib/python3/dist-packages/urllib3/util/connection.py", line 61, in create_connection
for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
File "/usr/lib/python3.8/socket.py", line 918, in getaddrinfo
for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
socket.gaierror: [Errno -2] Name or service not known

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 665, in urlopen
httplib_response = self._make_request(
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 376, in _make_request
self._validate_conn(conn)
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 996, in _validate_conn
conn.connect()
File "/usr/lib/python3/dist-packages/urllib3/connection.py", line 314, in connect
conn = self._new_conn()
File "/usr/lib/python3/dist-packages/urllib3/connection.py", line 171, in _new_conn
raise NewConnectionError(
urllib3.exceptions.NewConnectionError: <urllib3.connection.VerifiedHTTPSConnection object at 0x7f3fe8dd93a0>: Failed to establish a new connection: [Errno -2] Name or service not known

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/requests/adapters.py", line 489, in send
resp = conn.urlopen(
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 719, in urlopen
retries = retries.increment(
File "/usr/lib/python3/dist-packages/urllib3/util/retry.py", line 436, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='api.weather.com.cn', port=443): Max retries exceeded with url: /data/cityinfo/101280101.html (Caused by NewConnectionError('<urllib3.connection.VerifiedHTTPSConnection object at 0x7f3fe8dd93a0>: Failed to establish a new connection: [Errno -2] Name or service not known'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 84, in ask
return self.bot.run(query)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 156, in _call
next_step_output = self._take_next_step(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 122, in _take_next_step
observation = tool.run(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 73, in run
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 70, in run
observation = self._run(tool_input)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/meteo/meteo_weather.py", line 36, in _run
return self.api_chain.run(query)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/api/base.py", line 73, in _call
api_response = self.requests_wrapper.get(api_url)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/web_requests/wrapper.py", line 93, in get
response = requests.get(url, headers=self.headers, params=params, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/api.py", line 73, in get
return request("get", url, params=params, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/adapters.py", line 565, in send
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPSConnectionPool(host='api.weather.com.cn', port=443): Max retries exceeded with url: /data/cityinfo/101280101.html (Caused by NewConnectionError('<urllib3.connection.VerifiedHTTPSConnection object at 0x7f3fe8dd93a0>: Failed to establish a new connection: [Errno -2] Name or service not known'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 84, in ask
return self.bot.run(query)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 156, in _call
next_step_output = self._take_next_step(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 122, in _take_next_step
observation = tool.run(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 73, in run
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/base_tool.py", line 70, in run
observation = self._run(tool_input)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/tools/meteo/meteo_weather.py", line 36, in _run
return self.api_chain.run(query)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/api/base.py", line 66, in _call
api_url = self.api_request_chain.predict(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 151, in predict
return self(kwargs)[self.output_key]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 57, in _call
return self.apply([inputs])[0]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 118, in apply
response = self.generate(input_list)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 62, in generate
return self.llm.generate_prompt(prompts, stop)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 78, in generate_prompt
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 75, in generate_prompt
output = self.generate(prompt_messages, stop=stop)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 52, in generate
results = [self._generate(m, stop=stop) for m in messages]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 52, in
results = [self._generate(m, stop=stop) for m in messages]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 274, in _generate
response = self.completion_with_retry(messages=message_dicts, **params)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 234, in completion_with_retry
return _completion_with_retry(**kwargs)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 289, in wrapped_f
return self(f, *args, **kw)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 379, in call
do = self.iter(retry_state=retry_state)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 325, in iter
raise retry_exc.reraise()
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 158, in reraise
raise self.last_attempt.result()
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 437, in result
return self.__get_result()
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 389, in __get_result
raise self._exception
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 382, in call
result = fn(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 232, in _completion_with_retry
return self.client.create(**kwargs)
File "/usr/local/lib/python3.8/dist-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 619, in _interpret_response
self._interpret_response_line(
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 682, in _interpret_response_line
raise self.handle_error_response(
openai.error.RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-bP7cJd3Y9irUV7534hWo4ETp on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/chatgpt-on-wechat/plugins/tool/tool.py", line 88, in on_handle_context
_reply = self.app.ask(query, user_session)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 88, in ask
return self.ask(query, chat_history, retry_num + 1)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 91, in ask
raise TimeoutError("超过重试次数")
TimeoutError: 超过重试次数
[ERROR][2023-04-15 05:32:44][tool.py:93] - 超过重试次数
[DEBUG][2023-04-15 05:32:44][chat_channel.py:146] - [WX] ready to handle context: type=TEXT, content=请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理
[INFO][2023-04-15 05:32:44][chat_gpt_bot.py:35] - [CHATGPT] query=请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理
[DEBUG][2023-04-15 05:32:44][session_manager.py:66] - prompt tokens used=353
[DEBUG][2023-04-15 05:32:44][chat_gpt_bot.py:53] - [CHATGPT] session query=[{'role': 'system', 'content': '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'}, {'role': 'user', 'content': '使用meteo，告诉我今天广州的天气'}, {'role': 'user', 'content': '请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理'}, {'role': 'assistant', 'content': '哟～这个问题我可不大清楚喔，不好意思啊。 ChatGPT 我的确可以回答大部分问题，但是有些问题在当前的工具插件上还无法处理呢。\n\n听说你想知道广州今天的天气？很遗憾啊~ 我们的工具插件目前无法提供对天气预报的支持，因此我无法为您进行相关查询。\n\n不过别灰心，还有许多其他问题可以向我提出哦。我会尽我所能地帮助您解答疑问。'}, {'role': 'user', 'content': '使用meteo，告诉我今天广州的天气'}, {'role': 'user', 'content': '请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理'}]
[WARNING][2023-04-15 05:32:44][chat_gpt_bot.py:120] - [CHATGPT] RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-bP7cJd3Y9irUV7534hWo4ETp on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.
[WARNING][2023-04-15 05:32:49][chat_gpt_bot.py:139] - [CHATGPT] 第1次重试
[WARNING][2023-04-15 05:32:49][chat_gpt_bot.py:120] - [CHATGPT] RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-bP7cJd3Y9irUV7534hWo4ETp on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.
[WARNING][2023-04-15 05:32:54][chat_gpt_bot.py:139] - [CHATGPT] 第2次重试
[DEBUG][2023-04-15 05:33:03][chat_gpt_bot.py:62] - [CHATGPT] new_query=[{'role': 'system', 'content': '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'}, {'role': 'user', 'content': '使用meteo，告诉我今天广州的天气'}, {'role': 'user', 'content': '请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理'}, {'role': 'assistant', 'content': '哟～这个问题我可不大清楚喔，不好意思啊。 ChatGPT 我的确可以回答大部分问题，但是有些问题在当前的工具插件上还无法处理呢。\n\n听说你想知道广州今天的天气？很遗憾啊~ 我们的工具插件目前无法提供对天气预报的支持，因此我无法为您进行相关查询。\n\n不过别灰心，还有许多其他问题可以向我提出哦。我会尽我所能地帮助您解答疑问。'}, {'role': 'user', 'content': '使用meteo，告诉我今天广州的天气'}, {'role': 'user', 'content': '请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理'}], session_id=filehelper, reply_cont=Yo嘿嘿，这个问题我可是不大清楚呢。不过抱歉啊， ChatGPT的 tool 插件现在还处理不了这种问题哦。

似乎你想了解广州的天气，但是我无法为你提供相关预报，这可能是因为我的工具插件目前还不支持这种查询呢。

不用担心，我还有许多方法可以帮助你。不妨问问我其他问题，我会尽力提供帮助。, completion_tokens=145
[DEBUG][2023-04-15 05:33:03][session_manager.py:77] - raw total_tokens=498, savesession tokens=503
[DEBUG][2023-04-15 05:33:03][chat_channel.py:134] - [WX] ready to decorate reply: Reply(type=TEXT, content=Yo嘿嘿，这个问题我可是不大清楚呢。不过抱歉啊， ChatGPT的 tool 插件现在还处理不了这种问题哦。

似乎你想了解广州的天气，但是我无法为你提供相关预报，这可能是因为我的工具插件目前还不支持这种查询呢。

不用担心，我还有许多方法可以帮助你。不妨问问我其他问题，我会尽力提供帮助。)
[DEBUG][2023-04-15 05:33:03][chat_channel.py:225] - [WX] ready to send reply: Reply(type=TEXT, content=[bot] Yo嘿嘿，这个问题我可是不大清楚呢。不过抱歉啊， ChatGPT的 tool 插件现在还处理不了这种问题哦。

似乎你想了解广州的天气，但是我无法为你提供相关预报，这可能是因为我的工具插件目前还不支持这种查询呢。

不用担心，我还有许多方法可以帮助你。不妨问问我其他问题，我会尽力提供帮助。), context: Context(type=TEXT, content=请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WeChatMessage object at 0x7f3fe8e32d00>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': 'filehelper', 'receiver': 'filehelper'})
[INFO][2023-04-15 05:33:03][wechat_channel.py:164] - [WX] sendMsg=Reply(type=TEXT, content=[bot] Yo嘿嘿，这个问题我可是不大清楚呢。不过抱歉啊， ChatGPT的 tool 插件现在还处理不了这种问题哦。

似乎你想了解广州的天气，但是我无法为你提供相关预报，这可能是因为我的工具插件目前还不支持这种查询呢。

不用担心，我还有许多方法可以帮助你。不妨问问我其他问题，我会尽力提供帮助。), receiver=filehelper
[DEBUG][2023-04-15 05:33:03][chat_channel.py:241] - Worker return success, session_id = filehelper
[WARNING][2023-04-15 05:33:26][wechat_message.py:52] - [WX]get other_user_id failed: 'NickName'
[DEBUG][2023-04-15 05:33:26][wechat_channel.py:138] - [WX]receive text msg: {"MsgId": "8282463993774320030", "FromUserName": "@5cb59c41bbcaf32c0077b60f5507b3379f90af814f7e432a8f57c82d3237f0d2", "ToUserName": "filehelper", "MsgType": 1, "Content": "bot #debug", "Status": 3, "ImgStatus": 1, "CreateTime": 1681536806, "VoiceLength": 0, "PlayLength": 0, "FileName": "", "FileSize": "", "MediaId": "", "Url": "", "AppMsgType": 0, "StatusNotifyCode": 0, "StatusNotifyUserName": "", "RecommendInfo": {"UserName": "", "NickName": "", "QQNum": 0, "Province": "", "City": "", "Content": "", "Signature": "", "Alias": "", "Scene": 0, "VerifyFlag": 0, "AttrStatus": 0, "Sex": 0, "Ticket": "", "OpCode": 0}, "ForwardFlag": 0, "AppInfo": {"AppID": "", "Type": 0}, "HasProductId": 0, "Ticket": "", "ImgHeight": 0, "ImgWidth": 0, "SubMsgType": 0, "NewMsgId": 8282463993774320030, "OriContent": "", "EncryFileName": "", "User": {"UserName": "filehelper", "MemberList": []}, "Type": "Text", "Text": "bot #debug"}, cmsg=ChatMessage: id=8282463993774320030, create_time=1681536806, ctype=TEXT, content=bot #debug, from_user_id=@5cb59c41bbcaf32c0077b60f5507b3379f90af814f7e432a8f57c82d3237f0d2, from_user_nickname=LINK, to_user_id=filehelper, to_user_nickname=None, other_user_id=filehelper, other_user_nickname=None, is_group=False, is_at=False, actual_user_id=None, actual_user_nickname=None
[DEBUG][2023-04-15 05:33:26][chat_channel.py:282] - [WX] consume context: Context(type=TEXT, content=#debug, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WeChatMessage object at 0x7f3fe8e37130>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': 'filehelper', 'receiver': 'filehelper'})
[DEBUG][2023-04-15 05:33:26][chat_channel.py:130] - [WX] ready to handle context: Context(type=TEXT, content=#debug, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WeChatMessage object at 0x7f3fe8e37130>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': 'filehelper', 'receiver': 'filehelper'})
[DEBUG][2023-04-15 05:33:26][plugin_manager.py:157] - Plugin GODCMD triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-15 05:33:26][godcmd.py:196] - [Godcmd] on_handle_context. content: #debug
[DEBUG][2023-04-15 05:33:26][godcmd.py:349] - [Godcmd] admin command: debug by filehelper
[DEBUG][2023-04-15 05:33:26][chat_channel.py:134] - [WX] ready to decorate reply: Reply(type=INFO, content=DEBUG模式已开启)
[DEBUG][2023-04-15 05:33:26][chat_channel.py:225] - [WX] ready to send reply: Reply(type=INFO, content=[INFO]
DEBUG模式已开启), context: Context(type=TEXT, content=#debug, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WeChatMessage object at 0x7f3fe8e37130>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': 'filehelper', 'receiver': 'filehelper'})
[INFO][2023-04-15 05:33:26][wechat_channel.py:167] - [WX] sendMsg=Reply(type=INFO, content=[INFO]
DEBUG模式已开启), receiver=filehelper
[DEBUG][2023-04-15 05:33:26][chat_channel.py:241] - Worker return success, session_id = filehelper

tool 插件的问题, 采用tool命令，确生成聊天的summary

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [],
  "kwargs": {
      "debug": true  // debug模式一定要打开
  }
}

2. 你的问题：

[替换我]

正常启动插件，但是问题都变成被summary
3. 收到ai的回复：

![image](https://user-images.githubusercontent.com/15274284/234745136-148abda1-6878-48f0-9b30-7f6e46754340.png)

4. debug模式终端打印的日志：

[DEBUG][2023-04-27 02:24:56][chat_channel.py:262] - Worker return success, session_id = @838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee
[DEBUG][2023-04-27 02:25:01][wechat_channel.py:161] - [WX]receive text msg: {"MsgId": "5353332160588795729", "FromUserName": "@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee", "ToUserName": "@f8e8a4dc864139b4bc6d8d26044cac26e6c32c4d1c9b7d604cc5e4cb1f090b95", "MsgType": 1, "Content": "b $tool 使用metro，查询4月27日北京的天气", "Status": 3, "ImgStatus": 1, "CreateTime": 1682562300, "VoiceLength": 0, "PlayLength": 0, "FileName": "", "FileSize": "", "MediaId": "", "Url": "", "AppMsgType": 0, "StatusNotifyCode": 0, "StatusNotifyUserName": "", "RecommendInfo": {"UserName": "", "NickName": "", "QQNum": 0, "Province": "", "City": "", "Content": "", "Signature": "", "Alias": "", "Scene": 0, "VerifyFlag": 0, "AttrStatus": 0, "Sex": 0, "Ticket": "", "OpCode": 0}, "ForwardFlag": 0, "AppInfo": {"AppID": "", "Type": 0}, "HasProductId": 0, "Ticket": "", "ImgHeight": 0, "ImgWidth": 0, "SubMsgType": 0, "NewMsgId": 5353332160588795729, "OriContent": "", "EncryFileName": "", "User": {"MemberList": [], "Uin": 0, "UserName": "@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee", "NickName": "博洋", "HeadImgUrl": "/cgi-bin/mmwebwx-bin/webwxgeticon?seq=751762527&username=@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee&skey=@crypt_650a1e63_2de85d1cb97dde1c6714be1dc1aee511", "ContactFlag": 1, "MemberCount": 0, "RemarkName": "", "HideInputBarFlag": 0, "Sex": 1, "Signature": "人菜瘾大", "VerifyFlag": 0, "OwnerUin": 0, "PYInitial": "BY", "PYQuanPin": "boyang", "RemarkPYInitial": "", "RemarkPYQuanPin": "", "StarFriend": 0, "AppAccountFlag": 0, "Statues": 0, "AttrStatus": 102437, "Province": "北京", "City": "", "Alias": "", "SnsFlag": 257, "UniFriend": 0, "DisplayName": "", "ChatRoomId": 0, "KeyWord": "", "EncryChatRoomId": "", "IsOwner": 0}, "Type": "Text", "Text": "b $tool 使用metro，查询4月27日北京的天气"}, cmsg=ChatMessage: id=5353332160588795729, create_time=1682562300, ctype=TEXT, content=b $tool 使用metro，查询4月27日北京的天气, from_user_id=@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee, from_user_nickname=博洋, to_user_id=@f8e8a4dc864139b4bc6d8d26044cac26e6c32c4d1c9b7d604cc5e4cb1f090b95, to_user_nickname=RBQ3.0, other_user_id=@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee, other_user_nickname=博洋, is_group=False, is_at=False, actual_user_id=None, actual_user_nickname=None
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin SUMMARY triggered by event Event.ON_RECEIVE_MESSAGE
[DEBUG][2023-04-27 02:25:01][main.py:90] - [Summary] insert record: 博洋 5353332160588795729 博洋 b $tool 使用metro，查询4月27日北京的天气 TEXT 1682562300 1
[DEBUG][2023-04-27 02:25:01][chat_channel.py:307] - [WX] consume context: Context(type=TEXT, content=$tool 使用metro，查询4月27日北京的天气, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WechatMessage object at 0x7fa4aa9fab90>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': '@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee', 'receiver': '@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee'})
[DEBUG][2023-04-27 02:25:01][chat_channel.py:141] - [WX] ready to handle context: Context(type=TEXT, content=$tool 使用metro，查询4月27日北京的天气, kwargs={'isgroup': False, 'msg': <channel.wechat.wechat_message.WechatMessage object at 0x7fa4aa9fab90>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': '@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee', 'receiver': '@838b60254824f07db26549e650b2f45d7f54b32fc8e76c8b0b8a96871c45d6ee'})
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin GODCMD triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][godcmd.py:206] - [Godcmd] on_handle_context. content: $tool 使用metro，查询4月27日北京的天气
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin KEYWORD triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][keyword.py:52] - [keyword] on_handle_context. content: $tool 使用metro，查询4月27日北京的天气
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin SDWEBUI triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin ROLE triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin DUNGEON triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][dungeon.py:73] - [Dungeon] on_handle_context. content: ['$tool', '使用metro，查询4月27日北京的天气']
[DEBUG][2023-04-27 02:25:01][plugin_manager.py:163] - Plugin SUMMARY triggered by event Event.ON_HANDLE_CONTEXT
[DEBUG][2023-04-27 02:25:01][main.py:221] - [Summary] on_handle_context. content: $tool 使用metro，查询4月27日北京的天气
[DEBUG][2023-04-27 02:25:01][chat_gpt_session.py:63] - Warning: model not found. Using cl100k_base encoding.
[DEBUG][2023-04-27 02:25:01][main.py:195] - [Summary] summary all 75 messages
[DEBUG][2023-04-27 02:25:01][chat_gpt_session.py:63] - Warning: model not found. Using cl100k_base encoding.
[DEBUG][2023-04-27 02:25:01][main.py:199] - [Summary] session query: [{'role': 'system', 'content': '你是一位群聊机器人，需要对聊天记录进行简明扼要的总结，用列表的形式输出。\n聊天记录格式：[x]是emoji表情或者是对图片和声音文件的说明，消息最后出现表示消息触发了群聊机器人的回复，内容通常是提问，若带有特殊符号如#和$则是触发你无法感知的某个插件功能，聊天记录中不包含你对这类消息的回复，可降低这些消息的权重。请不要在回复中包含聊天记录格式中出现的符号。\n'}, {'role': 'user', 'content': '需要你总结的聊天记录如下：\n\n博洋: "b #auth 4621130" \n\n博洋: "b #installp sdwebui" \n\n博洋: "b #scanp" \n\n博洋: "b 画一个鸭子" \n\n博洋: "b 画 横版 高清 二次元:cat" \n\n博洋: "b #help" \n\n博洋: "b #plist" \n\n博洋: "b #help summary" \n\n博洋: "b 总结博洋
总结50"" \n\n博洋: "b "$总结 100"" \n\n博洋: "b $总结 100" \n\n博洋: "b #help tool" \n\n博洋: "b $tool 查一下今天的天气" \n\n博洋: "b $tool 用 meteo-weather 查看一下今天北京的天气情况 " \n\n博洋: "b $tool 用 meteo-weather 查看一下今天北京的天气情况 " \n\n博洋: "b $tool 查看一下今天北京的天气情况 " \n\n博洋: "b $tool 查看一下NBA比赛新闻" \n\n博洋: "b $tool reset" \n\n博洋: "b $tool 查一下今天的新闻" \n\n博洋: "[IMAGE]"\n\n博洋: "b #plist" \n\n博洋: "b #auth 4621130" \n\n博洋: "b #plist" \n\n博洋: "b #auth 4621130" \n\n博洋: "b #plist" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b #auth 4621130" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b 画个小鸭子" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair, up half body" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair, up half body" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画横版 高清 水墨：长城" \n\n博洋: "b #auth 4621130" \n\n博洋: "b #plist" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b #plist" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b #auth 4621130" \n\n博洋: "b #plist" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:girl,cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画横版 高清 水墨**画：greatwall" \n\n博洋: "[IMAGE]"\n\n博洋: "b #auth 4621130" \n\n博洋: "b #plist" \n\n博洋: "b #enablep sdwebui" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 画竖版 高清 二次元:cat ear,glasses, purple eye, black hair" \n\n博洋: "b 使用Terminal，查找我的用户目录有那些文件" \n\n博洋: "b $tool 使用Terminal，查找我的用户目录有那些文件" \n\n博洋: "b" \n\n博洋: "b #help tool" \n\n博洋: "b $tool 使用Terminal， ls -l" \n\n博洋: "b $tool 使用Terminal， ls -l" \n\n博洋: "b $tool 使用Terminal" \n\n博洋: "b $tool 激活tool插件" \n\n博洋: "b $tool" \n\n博洋: "b $tool 使用metro，查询4月27日北京的天气" \n\n博洋: "b #auth 4621130" \n\n博洋: "b $tool 使用metro，查询4月27日北京的天气" '}], prompt_tokens: 1876
[DEBUG][2023-04-27 02:25:20][main.py:202] - [Summary] total_tokens: 2276, completion_tokens: 400, reply_content: - 发送了指令#auth 4621130

发送了指令#installp sdwebui
发送了指令#scanp
发送了指令#help
发送了指令#plist
发送了指令#help summary
发送了指令$总结50
发送了指令$总结50
发送了指令$总结100
发送了指令$总结100
发送了指令#help tool
发送了指令$tool 查一下今天的天气
发送了指令$tool 用 meteo-weather 查看一下今天北京的天气情况
发送了指令$tool 查看一下今天北京的天气情况
发送了指令$tool 查看一下NBA比赛新闻
发送了指令$tool reset
发送了指令$tool 查一下今天的新闻

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

如果想让chatgpt自动补充当前或未来最新日期这个可以如何实现或者给他prompt

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

我想让chatgpt知道我们说的某一个事情是哪一天，比如我说明天我要去聚餐，我要让chatgpt自动改成 2023年5月14日要去聚餐。
现在我用tool工具里面的python是可以查询系统最新日期，但是chatgpt没有办法自动知道当前日期，能否在那个地方直接设置让他自动先调用工具查询今天最新日期，然后推测出我说的明天或后天对应是那个日期？

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [],
  "kwargs": {
      "debug": true  // debug模式一定要打开
  }
}

2. 你的问题：

[替换我]

3. 收到ai的回复：

[替换我]

4. debug模式终端打印的日志：

[替换我]

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

有个疑问，鉴于工具现在能自动执行终端和python命令，如何确保自动操作的安全性

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

有个疑问，鉴于工具现在能自动执行终端和python命令，如何确保自动操作的安全性

【需求】能否写一个调用网页版newbing的插件

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

能否写一个调用网页版newbing的插件，实现是否能够参考这个项目https://github.com/josStorer/chatGPTBox ，现在调用bing和google 获得的回答并不理想。

在chatgpt-wechat项目代码中更新chatgpt-tool插件

问题描述

怎么在chatgpt-wechat中更新这个chatgpt-tool插件呢？

无法识别到tool 插件，调用#reconf或者#scanp命令，未发现tool插件

升级了tool-hub0.4.1 还是没能启动tool，请问这个该怎么解决？

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key
   {
   "tools": ["python", "url-get", "terminal", "meteo-weather","wolfram-alpha"],
   "kwargs": {
   "top_k_results": 2,
   "openai_api_key": "1234",
   "proxy": "",
   "debug": true,
   "no_default": false,
   "model_name": "gpt-3.5-turbo",
   "wolfram_alpha_appid": "1234"
   }
   }

2. 你的问题：

```text
[升级了0.4.1的tool-hub，输入 bot$tool,报错，未知插件命令，输入bot # help tool，插件不存在活未启用，输入bot # help python，插件不存在活未启用]，我主要是想启动wolfram。请问这个该怎么解决？

3. 收到ai的回复：

[替换我]

4. debug模式终端打印的日志：

[替换我]

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

关于News新闻和天气的两个小问题

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

chatgpt-on-wechat：1.2.3.2
chatgpt-tool-hub：0.4.1

问题描述

AI在发送新闻内容的前面会带上一串字符，在获取天气的时候AI回复的是英文

{
"tools": [
"news",
"url-get",
"terminal",
"wikipedia",
"bing-search",
"meteo-weather",
"wolfram-alpha"

],
"kwargs": {
"top_k_results": 2,
"no_default": true,
"debug": true,
"searx_host": "",
"model_name": "gpt-3.5-turbo",
"bing_subscription_key": "81484fb4",
"news_api_key":"89eff01a",
"wolfram_alpha_appid":"Q93",
"google_api_key": "AIzaS",
"google_cse_id": "2300",
"zaobao_api_key": "0iLA5"
}
}

环境

• 操作系统类型 ：Ubuntu-22.04-x64
• Python版本 ：3.10
• pip版本 ( 执行 pip -V)：

[交流] 关于如何更好的使用tool的技巧

旧tool调优记录：

1. terminal

借助wechat和chatgpt-on-wechat，你获得了一个便携的向服务器执行shell命令的方法
如果你的服务器没有公网地址，那么你就获得一个内网穿透的替代方案
PS: 该tool已对危险指令实现了一个简单的过滤

1. 使用Terminal，查找我的用户目录有那些文件

您的用户目录下有许多文件和文件夹，包括Applications、Desktop、Documents、Downloads、Library、Movies、Music、Pictures等等。

2. 使用Terminal，告诉我当前用户名、所在组

我已经使用Terminal工具，获取到了当前用户名为goldfish，所在组为staff、everyone、localaccounts、_appserverusr、admin、_appserveradm、_lpadmin、com.apple.access_screensharing、_appstore、_lpoperator、_developer、_analyticsusers、com.apple.access_ftp、com.apple.access_ssh、com.apple.access_remote_ae。

3. 使用Terminal， ls -l

您输入了命令"ls -l"，我在终端中执行了该命令，并返回了当前目录下的文件列表及其详细信息。

PS: 可在日志查看terminal确实执行该指令

4. 使用Terminal， 帮我查看chatgpt_tool_hub目录version.py文件包含内容是什么

无法使用Terminal查看chatgpt_tool_hub目录下的version.py文件，因为该目录不存在。请确认该目录是否存在或者输入是否正确。

5. 使用Terminal，帮我查看当前目录version.py文件包含内容是什么

当前目录下的version.py文件包含的内容是__version__ = ‘0.3.7’。

6. 使用Terminal，帮我查看当前目录version.py文件包含内容是什么（设置terminal了超时时间）

很抱歉，由于执行命令的时间超过了0.0001秒的限制，我无法查看当前目录下version.py文件的内容。请您尝试其他方法或者缩小文件范围。

terminal的调优将更新在chatgpt_tool_hub 0.3.7版本，如果你需要体验可执行更新tool插件依赖包的命令，之后重启chatgpt-on-wechat项目

pip install -i https://pypi.python.org/simple chatgpt_tool_hub==0.3.7

2. meteo-weather

回答你有关天气的询问, 需要获取时间、地点上下文信息，本工具使用了meteo open api

1. 使用meteo，查询4月10号杭州的天气情况

2023年4月10日杭州的天气情况是多云，气温在12.3°C到27.0°C之间。

meteo 接口返回：

{"latitude":30.25,"longitude":120.125,"generationtime_ms":0.14698505401611328,"utc_offset_seconds":28800,"timezone":"Asia/Shanghai","timezone_abbreviation":"CST","elevation":13.0,"hourly_units":{"time":"iso8601","temperature_2m":"°C"},"hourly":{"time":["2023-04-10T00:00","2023-04-10T01:00","2023-04-10T02:00","2023-04-10T03:00","2023-04-10T04:00","2023-04-10T05:00","2023-04-10T06:00","2023-04-10T07:00","2023-04-10T08:00","2023-04-10T09:00","2023-04-10T10:00","2023-04-10T11:00","2023-04-10T12:00","2023-04-10T13:00","2023-04-10T14:00","2023-04-10T15:00","2023-04-10T16:00","2023-04-10T17:00","2023-04-10T18:00","2023-04-10T19:00","2023-04-10T20:00","2023-04-10T21:00","2023-04-10T22:00","2023-04-10T23:00"],"temperature_2m":[12.3,11.6,11.3,11.0,10.7,10.5,10.3,11.6,14.5,17.6,20.6,23.1,24.8,26.1,26.8,27.0,26.3,24.8,22.7,20.6,18.9,18.5,17.9,17.6]},"daily_units":{"time":"iso8601"},"daily":{"time":["2023-04-10"]}}

chatgpt能自己推断出城市到经纬度的映射关系确实很神奇

2. 使用meteo，明天北京会下雨吗？

根据API的响应，无法确定明天北京是否会下雨。API调用仅提供2023年4月10日的降水和天气代码信息，但没有指定是否会下雨。

meteo 接口返回：

{"latitude":39.875,"longitude":116.375,"generationtime_ms":0.1609325408935547,"utc_offset_seconds":28800,"timezone":"Asia/Shanghai","timezone_abbreviation":"CST","elevation":47.0,"hourly_units":{"time":"iso8601","precipitation":"mm"},"hourly":{"time":["2023-04-10T00:00","2023-04-10T01:00","2023-04-10T02:00","2023-04-10T03:00","2023-04-10T04:00","2023-04-10T05:00","2023-04-10T06:00","2023-04-10T07:00","2023-04-10T08:00","2023-04-10T09:00","2023-04-10T10:00","2023-04-10T11:00","2023-04-10T12:00","2023-04-10T13:00","2023-04-10T14:00","2023-04-10T15:00","2023-04-10T16:00","2023-04-10T17:00","2023-04-10T18:00","2023-04-10T19:00","2023-04-10T20:00","2023-04-10T21:00","2023-04-10T22:00","2023-04-10T23:00"],"precipitation":[0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00,0.00]},"daily_units":{"time":"iso8601","weathercode":"wmo code"},"daily":{"time":["2023-04-10"],"weathercode":[3]}}

注：严谨的chatgpt没有觉得全天降雨量均为0能推断出明天北京是否会下雨。

一番prompt tuning后：

抱歉，根据OpenMeteo API的响应，无法确定明天北京是否会下雨。API只提供未来24小时的天气代码和降水数据，但它不指示明天是否会下雨。因此，我无法提供明确的答案。API响应只包括2023年4月11日的每小时天气数据，并没有提供明天是否会下雨的明确指示。

PS：我从tuning结果分析，觉得chatgpt有道理。这一块我没有用prompt暗示chatgpt能从降雨数据推断出下雨

3. 使用meteo，明天北京云量怎么样？

我很抱歉，我无法回答您的问题。我尝试使用meteo-weather工具获取明天北京的云量信息，但是该API无法提供云量信息。我还尝试使用url-get工具搜索相关信息，但是搜索结果并没有提供明确的答案。很抱歉无法帮助您解决问题。

中间过程出现错误，一番prompt tuning后：

{"latitude":39.875,"longitude":116.375,"generationtime_ms":0.1800060272216797,"utc_offset_seconds":28800,"timezone":"Asia/Shanghai","timezone_abbreviation":"CST","elevation":47.0,"hourly_units":{"time":"iso8601","cloudcover":"%"},"hourly":{"time":["2023-04-11T00:00","2023-04-11T01:00","2023-04-11T02:00","2023-04-11T03:00","2023-04-11T04:00","2023-04-11T05:00","2023-04-11T06:00","2023-04-11T07:00","2023-04-11T08:00","2023-04-11T09:00","2023-04-11T10:00","2023-04-11T11:00","2023-04-11T12:00","2023-04-11T13:00","2023-04-11T14:00","2023-04-11T15:00","2023-04-11T16:00","2023-04-11T17:00","2023-04-11T18:00","2023-04-11T19:00","2023-04-11T20:00","2023-04-11T21:00","2023-04-11T22:00","2023-04-11T23:00"],"cloudcover":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]},"daily_units":{"time":"iso8601"},"daily":{"time":["2023-04-11"]}}

根据OpenMeteo API的响应，似乎无法回答这个问题，因为2023年4月11日北京的云量信息不可用。 API响应仅包括2023年4月11日的每小时云量数据，所有小时的值均为0。因此，明天北京的云量信息不可用。

PS：输出结果的可解释性更强了，我认为从所有小时的值均为0推断出云量信息不可用有道理。

4. 使用meteo，昨天北京日出时间是多少？

{"latitude":39.875,"longitude":116.375,"generationtime_ms":0.16307830810546875,"utc_offset_seconds":28800,"timezone":"Asia/Shanghai","timezone_abbreviation":"CST","elevation":47.0,"daily_units":{"time":"iso8601","sunrise":"iso8601"},"daily":{"time":["2023-04-09","2023-04-10","2023-04-11","2023-04-12","2023-04-13","2023-04-14","2023-04-15","2023-04-16"],"sunrise":["2023-04-09T05:45","2023-04-10T05:43","2023-04-11T05:42","2023-04-12T05:40","2023-04-13T05:38","2023-04-14T05:37","2023-04-15T05:35","2023-04-16T05:34"]}}

根据您的要求，我使用了meteo-weather工具来获取昨天北京的日出时间。根据API的响应，昨天北京的日出时间是05:45。

PS：回答精准，不过你们应该看不见中间prompt失败的过程，真的不来tool的仓库点一个star吗？chatgpt-tool-hub

tuning后meteo的实用性大大增强了，由于最近项目重构有些接口改变，暂时不打新版本的包

注：该工具比较耗时、耗token

3. morning-news

这是一个最近从issue 800看到的一个需求，这个需求获取的内容很简单，每天1点更新一次当日新闻，我觉得挺实用就跟进了

PS：如果有类似的需求欢迎PR到chatgpt-tool-hub，仅用半小时就能实现

1. 给我今天的早报

早报日期：2023-04-11
微语：撑不住的时候可以说“我好累”，但永远不要说“我不行”。

早报新闻列表：
1、**气象台发布沙尘暴蓝色预警，预计至11日，15省区市有扬沙或浮尘天气，内蒙古局部有强沙尘暴；北京空气质量陷入重度污染，大风沙尘持续至11日傍晚结束，景区关停大型游乐设施等户外游乐项目；
2、国铁集团：4月13日起中老铁路开行国际旅客列车，全程10小时30分，昆明至万象间可实现当日通达；
3、发改委：为杜绝浪费，单桌1500元以上(不含酒水)宴会套餐拟被重点监管；
4、东部战区：圆满完成环台岛战备警巡和“联合利剑“演习各项任务，全面检验了实战条件下多兵种联合作战能力；台媒：歼-15从山东舰起飞进入台东南空域，验证不用导弹就能锁台；美议员称支持向**派兵，“愿为**而战“，网友批：战争贩子！；
5、前**首富、汉能系创始人李河君被有关部门带走数月后，汉能系9家原主体公司将破产清算；
6、北京市住建委：多子女家庭购房“一区一策“措施或将在房山区试点；
7、一辆河南自驾游轿车在山西晋城坠崖，或因驾驶员操作不当引起，救援人员：落差近百米，约有20层楼高，车内2人死亡；
8、**足协明确：俱乐部不得就裁判判罚提出抗议。职业联赛争议判罚申诉制度推行一年后被废止；
9、比亚迪发布“云辇“智能车身控制系统，王传福：更舒适更安全，掉了一个轮子车辆仍能正常行驶；
10、韩国海警又以所谓“非法捕捞“为由扣押3艘**渔船；
11、巴基斯坦西南部俾路支省首府奎达发生爆炸袭击事件，致4死15伤；美国肯塔基州当地10日发生枪击事件，造成至少5死6伤；
12、俄媒：以购买力平价计算，金砖国家经济总量已超七国集团；俄媒：不到一个月时间，客户从美国银行系统提走近5000亿美元，50年来美国最严重的存款流出；
13、NASA：一个“逃逸“黑洞正撕裂宇宙，距离地球75亿光年；
14、拜登称他计划参加2024年美国大选，“但尚未准备好正式宣布”，若其参选，或将依靠数百名“网红“帮助宣传；
15、德国计划于今年6月12日至24日，主导北约史上最大规模空中军演，届时将有24个参演国出动220余架战机；

早报图片：https://file.alapi.cn/60s/202304111681149603.png

terminal的调优将更新在chatgpt_tool_hub 0.3.9版本，如果你需要体验meteo最新的调优效果和morning-news工具可执行更新tool插件依赖包的命令，之后重启chatgpt-on-wechat项目

pip install -i https://pypi.python.org/simple chatgpt_tool_hub==0.3.9

执行指令失败

为什么有些指令会这么回复

Action Input: curl google.com), receiver=@3e06c0e43443ade5f24389fc5228e75f3dd800eda69d84a44295a181f47f68b5
[INFO][2023-04-10 14:38:58][base.py:99] - 执行Tool: requests_get中...
[INFO][2023-04-10 14:38:58][bot.py:87] - 行动输入: https://finance.sina.cn/tech/2023-04-09/detail-imypvaue8116083.d.html

[INFO][2023-04-10 14:39:03][bot.py:87] - 行动输入: None
[INFO][2023-04-10 14:39:09][wechat_channel.py:164] - [WX] sendMsg=Reply(type=TEXT, content=the response to the original input question in chineseNew input: 总结这个链接的内容 https://finance.sina.cn/tech/2023-04-09/detail-imypvaue8116083.d.html
Thought: Do I need to use a tool? Yes
Action: requests_get
Action Input: https://finance.sina.cn/tech/2023-04-09/detail-imypvaue8116083.d.html), receiver=@3e06c0e43443ade5f24389fc5228e75f3dd800eda69d84a44295a181f47f68b5
[WARNING][2023-04-10 14:39:50][wechat_message.py:52] - [WX]get other_user_id failed: 'UserName'
[WARNING][2023-04-10 14:41:53][wechat_message.py:52] - [WX]get other_user_id failed: 'UserName'

项目依赖均已更新至最新，tool工具用不起来，提示未知插件命令！

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [
    "python",
    "url-get",
    "terminal",
    "meteo-weather",
    "requests",
    "morning-news",
    "wikipedia",
    "bing-search",
    "wolfram-alpha"
  ],
  "kwargs": {
    "top_k_results": 2,
    "no_default": false,
    "model_name": "gpt-3.5-turbo",
    "zaobao_api_key": "1234"
  }
}

2. 你的问题：

我pip3 install -r requirements.txt，pip3 install -r requirements-optional.txt这两个依赖都更新了，项目也用git pull更新了，都正常，但是启动后$tool，就是不能用。我输入$tool,
查看日志：
[INFO][2023-04-23 03:39:11][wechat_channel.py:196] - [WX] sendMsg=Reply(type=ERROR, content=[ERROR]
未知插件命令
查看插件命令列表请输入#help 插件名
), receiver=@9905db42e440cdcd2aacd2df992549f1

3. 收到ai的回复：
[ERROR]
未知插件命令
查看插件命令列表请输入#help 插件名.]。
之前默认的4个还可以用，现在全部不能用了，这是啥原因？

4. debug模式终端打印的日志：

```text
[替换我]

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

chatgpt-on-wechat中扩展tool工具无法生效

前置确认

1. 网络能够访问openai接口

可以

2. git pull 拉取最新代码

已拉取

3. 执行pip install -r requirements.txt，检查依赖是否满足

满足

4. 在已有 issue 中未搜索到类似问题

不能

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

chatgpt-on-wechat中tool/下增减config.json未生效

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
    "tools":[
        "news",
        "google-search",
        "morning-news"
    ],
    "kwargs":{
        "debug":false,
        "request_timeout":120,
        "no_default":false,
        "model_name":"gpt-3.5-turbo",
        "news_api_key":" ",
        "google_api_key":" ",
        "google_cse_id":" ",
        "morning_news_api_key":" "
    }
}

4. debug模式终端打印的日志：

[INFO][2023-05-26 04:24:09][config.py:180] - [INIT] override config by environ args: group_chat_in_one_session=["ALL_GROUP"]
[INFO][2023-05-26 04:24:09][config.py:180] - [INIT] override config by environ args: group_name_white_list=["ALL_GROUP"]
[INFO][2023-05-26 04:24:09][config.py:180] - [INIT] override config by environ args: open_ai_api_key= 
[INFO][2023-05-26 04:24:09][config.py:195] - [INIT] load config: {'open_ai_api_key': '', 'model': 'gpt-3.5-turbo', 'proxy': '', 'single_chat_prefix': ['bot', '@bot'], 'single_chat_reply_prefix': '[bot] ', 'group_chat_prefix': ['@bot'], 'group_name_white_list': ['ALL_GROUP'], 'group_chat_in_one_session': ['ALL_GROUP'], 'image_create_prefix': ['画', '看', '找'], 'speech_recognition': False, 'group_speech_recognition': False, 'voice_reply_voice': False, 'conversation_max_tokens': 1000, 'expires_in_seconds': 3600, 'character_desc': '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。', 'subscribe_msg': '感谢您的关注！\n这里是ChatGPT，可以自由对话。\n支持语音对话。\n支持图片输入。\n支持图片输出，画字开头的消息将按要求创作图片。\n支持tool、角色扮演和文字冒险等丰富的插件。\n输入{trigger_prefix}#help 查看详细指令。'}
[INFO][2023-05-26 04:24:09][config.py:145] - [Config] User datas file not found, ignore.
█
[INFO][2023-05-26 04:24:11][plugin_manager.py:50] - Loading plugins config...
[INFO][2023-05-26 04:24:11][plugin_manager.py:66] - Scaning plugins ...
chatgpt-tool-hub version: 0.4.3
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin tool_v0.4 registered, path=./plugins/tool
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin Keyword_v0.1 registered, path=./plugins/keyword
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin Hello_v0.1 registered, path=./plugins/hello
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin Godcmd_v1.0 registered, path=./plugins/godcmd
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin Dungeon_v1.0 registered, path=./plugins/dungeon
[INFO][2023-05-26 04:24:14][plugin_manager.py:41] - Plugin Banwords_v1.0 registered, path=./plugins/banwords
[INFO][2023-05-26 04:24:15][plugin_manager.py:41] - Plugin Role_v1.0 registered, path=./plugins/role
[INFO][2023-05-26 04:24:15][plugin_manager.py:41] - Plugin Finish_v1.0 registered, path=./plugins/finish
[INFO][2023-05-26 04:24:15][plugin_manager.py:41] - Plugin BDunit_v0.1 registered, path=./plugins/bdunit
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin GODCMD not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin KEYWORD not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin BANWORDS not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin TOOL not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin ROLE not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin DUNGEON not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin BDUNIT not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin HELLO not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][plugin_manager.py:101] - Plugin FINISH not found in pconfig, adding to pconfig...
[INFO][2023-05-26 04:24:15][godcmd.py:181] - [Godcmd] 因未设置口令，本次的临时口令为2894。
[INFO][2023-05-26 04:24:15][godcmd.py:196] - [Godcmd] inited
[INFO][2023-05-26 04:24:15][keyword.py:40] - [keyword] {}
[INFO][2023-05-26 04:24:15][keyword.py:42] - [keyword] inited.
[WARNING][2023-05-26 04:24:15][banwords.py:53] - [Banwords] init failed, ignore or see https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/banwords .
[ERROR][2023-05-26 04:24:15][plugin_manager.py:126] - Failed to init BANWORDS, diabled. [Errno 2] No such file or directory: '/app/plugins/banwords/banwords.txt'
Traceback (most recent call last):
File "/app/plugins/plugin_manager.py", line 124, in activate_plugins
instance = plugincls()
File "/app/plugins/banwords/banwords.py", line 54, in __init__
raise e
File "/app/plugins/banwords/banwords.py", line 40, in __init__
with open(banwords_path, "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/app/plugins/banwords/banwords.txt'
[INFO][2023-05-26 04:24:15][__init__.py:29] - [visual_dl] init failed, error_info: ModuleNotFoundError("No module named 'torch'")
[INFO][2023-05-26 04:24:15][__init__.py:29] - [visual_dl] init failed, error_info: ModuleNotFoundError("No module named 'torch'")
[WARNING][2023-05-26 04:24:16][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[WARNING][2023-05-26 04:24:16][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[INFO][2023-05-26 04:24:16][victorinox.py:86] - use_tools=['python', 'meteo-weather', 'terminal', 'url-get'], params: {'debug': False, 'openai_api_key': ' ', 'open_ai_api_base': 'https://api.openai.com/v1';, 'proxy': '', 'request_timeout': 120, 'model_name': 'gpt-3.5-turbo', 'no_default': False, 'top_k_results': 3, 'news_api_key': '', 'bing_subscription_key': '', 'google_api_key': '', 'google_cse_id': '', 'searx_search_host': '', 'wolfram_alpha_appid': '', 'morning_news_api_key': '', 'cuda_device': 'cpu', 'think_depth': 3, 'arxiv_summary': True, 'morning_news_use_llm': False}
[INFO][2023-05-26 04:24:16][tool.py:32] - [tool] inited
[INFO][2023-05-26 04:24:16][role.py:69] - [Role] inited
[INFO][2023-05-26 04:24:16][dungeon.py:56] - [Dungeon] inited
[WARNING][2023-05-26 04:24:16][bdunit.py:47] - [BDunit] init failed, ignore
[ERROR][2023-05-26 04:24:16][plugin_manager.py:126] - Failed to init BDUNIT, diabled. config.json not found
Traceback (most recent call last):
File "/app/plugins/plugin_manager.py", line 124, in activate_plugins
instance = plugincls()
File "/app/plugins/bdunit/bdunit.py", line 48, in __init__
raise e
File "/app/plugins/bdunit/bdunit.py", line 36, in __init__
raise Exception("config.json not found")
Exception: config.json not found
[INFO][2023-05-26 04:24:16][hello.py:23] - [Hello] inited
[INFO][2023-05-26 04:24:16][finish.py:23] - [Finish] inited
Ready to login.
Getting uuid of QR code.
Downloading QR code.
You can also scan QRCode in any website below:
█▀▀▀▀▀▀▀█▀█▀██▀█▀▀█████▀▀▀▀▀▀▀█
█ █▀▀▀█ ██   ▀█ ▀█▀ ▄██ █▀▀▀█ █
█ █   █ █  █   █▀ ▀▀█▄█ █   █ █
█ ▀▀▀▀▀ █ █ ▄ ▄ █▀▄▀▄ █ ▀▀▀▀▀ █
█▀███▀█▀▀ █▄ ▄█  ▄ █▄ ▀▀▀▀▀██▀█
█▀▄▄▄▄ ▀▀  ▄ ▄▄▀ ▄█▄█▄█▄▄▄▄▄▄ █
█▄█ ▀██▀▀▀ ▀███▄▄▄ ▄▄ ▄█▄▄▄█ ▄█
███▀█▄ ▀▀▀▄▄▄▄ ▀▀▄▄ █▀█▄▄   ▄ █
██ ▄▄▀ ▀▄▄  ▄▄█ ▄▀ ▄█▀ █████ ▄█
█▄▄███▄▀▀▀█▀█▀█▀ ▄  ██▄ ▄ ▄▀▄ █
█▀▀▀▀▄▄▀▀ ▄ █▀█ █▄  █▀▀▀▀ ▀█▄ █
█▀▀▀▀▀▀▀█   ███▀ ▄▄ ▀ █▀█ ▀▀█ █
█ █▀▀▀█ █▀▄▀▄▀▀ ▀█ ▄  ▀▀▀ ▀█▄▀█
█ █   █ ██▀  █▀  ▄  █  ███▀▀▀ █
█ ▀▀▀▀▀ █▀▀▄▄▀█ ▀█ ▀█ ▀▄ █ █ ▄█
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
Log in time out, reloading QR code.
Getting uuid of QR code.

环境

railway docker部署

tool.py运行失败

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

ubuntu@ip-172-31-24-107:~/chatgpt-on-wechat/plugins/tool$ python3 tool.py
chatgpt-tool-hub version: 0.4.1
Traceback (most recent call last):
File "/home/ubuntu/chatgpt-on-wechat/plugins/tool/tool.py", line 8, in
import plugins
ModuleNotFoundError: No module named 'plugins'
求助

• 操作系统类型 (Mac/Windows/Linux)：ubuntu
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

天气获取了不返回信息，只告诉我获取成功了。

问题描述

问天气，只告诉我获取成功了。

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [
    "google-search",
    "morning-news",
    "searxng-search"
  ],
  "kwargs": {
    "openai_api_key": "sk-",
    "proxy": "http://127.0.0.1:7890",
    "debug": false,
    "no_default": false,
    "model_name": "gpt-3.5-turbo",
    "google_api_key": "",
    "google_cse_id": "",
    "common_proxy": "http://127.0.0.1:7890",
    "zaobao_api_key": "",
    "request_timeout": 1000,
    "searx_search_host": "http://127.0.0.1:32283"
  }
}

2. 你的问题：

 $tools   今天北京天气

3. 收到ai的回复：

 根据您的输入，我已经为您获取了北京今天的天气信息。如果您还需要其他帮助，请告诉我。

4. debug模式终端打印的日志：

环境

• 操作系统类型 (/Linux)：
• Python版本 ( 执行 python -V )： Python 3.8.0
• pip版本 ( 执行 pip -V)：pip 23.0.1

arxiv 工具初始化失败

建议加上安全限制

你好，目前工具是链接了个人订阅号，如果开启了tool，对于熟悉tool的用户来说，可能会使用这个tool来读取订阅号所在服务器的信息，甚至做一些非法操作。建议可以加上安全限制，比如使用口令，减少危险，也方便推广。谢谢。

关于插件的使用：请问google和terminal等插件都必须通过&tool 前缀唤起吗？直接对话均无法生效

[INFO][2023-05-27 04:07:45][passive_reply.py:97] - [wechatmp] Request 1 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279246620709 162.62.81.123:13936
使用google搜索明天北京的天气
[INFO][2023-05-27 04:07:45][chat_gpt_bot.py:49] - [CHATGPT] query=使用google搜索明天北京的天气
[INFO][2023-05-27 04:07:50][passive_reply.py:97] - [wechatmp] Request 2 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279246620709 162.62.80.8:50937
使用google搜索明天北京的天气
[INFO][2023-05-27 04:07:53][wechatmp_channel.py:84] - [wechatmp] text cached, receiver oW95L1Iovxvkd-mMpZqKXlhc_4AY
很抱歉，由于我是离线模型，无法直接进行网络搜索。但是我可以告诉你可以打开Google搜索页面并输入 "明天北京的天气" 来查找有关明天北京天气的信息。
[INFO][2023-05-27 04:07:53][passive_reply.py:151] - [wechatmp] Request 2 do send to oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279246620709: 使用google搜索明天北京的天气
很抱歉，由于我是离线模型，无法直接进行网络搜索。但是我可以告诉你可以打开Google搜索页面并输入 "明天北京的天气" 来查找有关明天北京天气的信息。

[INFO][2023-05-27 04:07:56][passive_reply.py:97] - [wechatmp] Request 1 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279276258309 162.62.80.8:51456
&tool 使用google搜索明天北京的天气
[INFO][2023-05-27 04:08:01][passive_reply.py:97] - [wechatmp] Request 2 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279276258309 162.62.81.123:16492
&tool 使用google搜索明天北京的天气
[INFO][2023-05-27 04:08:06][passive_reply.py:97] - [wechatmp] Request 3 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125279276258309 162.62.81.123:17278
&tool 使用google搜索明天北京的天气
[INFO][2023-05-27 04:08:12][wechatmp_channel.py:84] - [wechatmp] text cached, receiver oW95L1Iovxvkd-mMpZqKXlhc_4AY
明天北京的天气为小雨，温度为25℃。
[INFO][2023-05-27 04:08:14][passive_reply.py:97] - [wechatmp] Request 1 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125285506234412 162.62.80.57:60892
1
[INFO][2023-05-27 04:08:14][passive_reply.py:151] - [wechatmp] Request 1 do send to oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125285506234412: 1
明天北京的天气为小雨，温度为25℃。

[INFO][2023-05-27 04:29:19][passive_reply.py:97] - [wechatmp] Request 1 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125302526223939 162.62.80.57:50056
&tool 使用terminal查询今天日期
[INFO][2023-05-27 04:29:24][passive_reply.py:97] - [wechatmp] Request 2 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125302526223939 162.62.80.57:50754
&tool 使用terminal查询今天日期
[INFO][2023-05-27 04:29:29][passive_reply.py:97] - [wechatmp] Request 3 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125302526223939 162.62.80.8:12213
&tool 使用terminal查询今天日期
[INFO][2023-05-27 04:29:31][wechatmp_channel.py:84] - [wechatmp] text cached, receiver oW95L1Iovxvkd-mMpZqKXlhc_4AY
今天的日期是：Sat May 27 04:29:24 +08 2023

[INFO][2023-05-27 04:29:42][passive_reply.py:97] - [wechatmp] Request 1 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125303223971757 162.62.81.123:6994
使用terminal查询今天日期
[INFO][2023-05-27 04:29:42][chat_gpt_bot.py:49] - [CHATGPT] query=使用terminal查询今天日期
[INFO][2023-05-27 04:29:47][passive_reply.py:97] - [wechatmp] Request 2 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125303223971757 162.62.80.8:13592
使用terminal查询今天日期
[INFO][2023-05-27 04:29:53][passive_reply.py:97] - [wechatmp] Request 3 from oW95L1Iovxvkd-mMpZqKXlhc_4AY 24125303223971757 162.62.80.57:55234
使用terminal查询今天日期
[INFO][2023-05-27 04:29:54][wechatmp_channel.py:84] - [wechatmp] text cached, receiver oW95L1Iovxvkd-mMpZqKXlhc_4AY
要在终端中查询今天的日期，您可以使用内置的date命令。只需打开终端并输入以下命令：

date

按“Enter”键后，终端将输出当前日期和时间，例如：

Sat May 27 04:29:24 +08 2023

请注意，输出日期和时间的格式和时区可能因您的计算机设置而有所不同。

[morning-news] init failed, error_info: ValueError('Did not find zaobao_api_key, please add an environment variable `ZAOBAO_API_KEY` which contains it, or pass `zaobao_api_key` as a named parameter.')

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [],
  "kwargs": {
      "debug": true  // debug模式一定要打开
  }
}

2. 你的问题：
   log里面老是读不到可以 是要在哪里配置

[morning-news] init failed, error_info: ValueError('Did not find zaobao_api_key, please add an environment variable `ZAOBAO_API_KEY` which contains it, or pass  `zaobao_api_key` as a named parameter.')
[news-api] init failed, error_info: ValueError('Did not find news_api_key, please add an environment variable `NEWS_API_KEY` which contains it, or pass  `news_api_key` as a named parameter.')

3. 收到ai的回复：

[替换我]

4. debug模式终端打印的日志：

[替换我]

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

请问 config.json文件放在chatgpt-on-wechat 项目的哪个目录下

https://github.com/goldfishh/chatgpt-on-wechat/blob/master/plugins/tool/README.md#configjson-%E9%85%8D%E7%BD%AE%E8%AF%B4%E6%98%8E

请问 config.json文件放在chatgpt-on-wechat 项目的哪个目录下，我放在plugins文件夹里，插件google_search文件夹也放了一个，但是聊天的时候输入$tool google-search 都没能触发谷歌搜索

配置如下：
{
"tools": ["google-search"], // 填入你想用到的额外工具名
"kwargs": {
"request_timeout": 60, // openai接口超时时间
"no_default": false, // 是否不使用默认的4个工具
"google_api_key": "AIzaSyBWVa_dQDG2SC***************",
"google_cse_id": "37bdde62**************"
}
}

工具思考的时候，触发了openai的频率限制，希望加个向chatgpt调用的频率限制，避免再命中频控

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

问：今天兰州天气怎么样？
我看他思考的时候，触发了openai的频率限制，希望加个向chatgpt调用的频率限制，避免再命中频控

2. 你的问题：

兰州今天天气怎么样？

3. 收到ai的回复：

兰州当前温度为21.7°C，天气代码为3，表示有阵雨。未来24小时每个小时的温度和天气代码也已经获取到了，您可以根据这些信息了解兰州未来的天气情况。

4. debug模式终端打印的日志：

[INFO][2023-05-12 14:56:53][chat_channel.py:106] - [WX]receive group at
[INFO][2023-05-12 14:56:53][victorinox.py:111] - 提问: 兰州今天天气怎么样？
[INFO][2023-05-12 14:56:58][base.py:226] - LLM-OS的内心独白: 推理：用户输入了一个关于天气的问题，需要使用天气查询工具来获取信息
思考：用户想要查询兰州今天的天气信息
反思：需要确认用户想要查询的是今天的天气，还是其他时间段的天气信息

[INFO][2023-05-12 14:56:58][base.py:177] - 执行Tool: meteo-weather中...
[INFO][2023-05-12 14:56:58][base.py:115] - 输入: 兰州今天天气
[INFO][2023-05-12 14:56:58][tool_engine.py:134] - 我将给工具发送如下信息: 
兰州今天天气
[INFO][2023-05-12 14:57:01][base.py:77] - URL 构造: https://api.open-meteo.com/v1/forecast?latitude=36.0611&longitude=103.8343&hourly=temperature_2m,weathercode&current_weather=true&temperature_unit=celsius&timeformat=iso8601&timezone=Asia/Shanghai&start_date=2023-05-12&end_date=2023-05-12
[INFO][2023-05-12 14:57:02][base.py:87] - API 响应: '{"latitude":36.125,"longitude":104.0,"generationtime_ms":0.19800662994384766,"utc_offset_seconds":28800,"timezone":"Asia/Shanghai","timezone_abbreviation":"CST","elevation":1520.0,"current_weather":{"temperature":21.7,"windspeed":10.1,"winddirection":287.0,"weathercode":3,"is_day":1,"time":"2023-05-12T14:00"},"hourly_units":{"time":"iso8601","temperature_2m":"°C","weathercode":"wmo code"},"hourly":{"time":["2023-05-12T00:00","2023-05-12T01:00","2023-05-12T02:00","2023-05-12T03:00","2023-05-12T04:00","2023-05-12T05:00","2023-05-12T06:00","2023-05-12T07:00","2023-05-12T08:00","2023-05-12T09:00","2023-05-12T10:00","2023-05-12T11:00","2023-05-12T12:00","2023-05-12T13:00","2023-05-12T14:00","2023-05-12T15:00","2023-05-12T16:00","2023-05-12T17:00","2023-05-12T18:00","2023-05-12T19:00","2023-05-12T20:00","2023-05-12T21:00","2023-05-12T22:00","2023-05-12T23:00"],"temperature_2m":[11.7,10.8,10.7,10.2,9.6,8.6,7.9,7.5,10.2,12.5,15.0,17.7,19.7,20.9,21.7,22.2,22.4,22.1,21.7,21.0,19.6,17.4,15.3,14.2],"weathercode":[3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,2,3]}}'
[INFO][2023-05-12 14:57:08][tool_engine.py:163] - 工具 meteo-weather 返回内容: 根据API的响应结果，我们可以看到兰州的经纬度信息以及当前时间的天气情况。其中，当前时间的天气情况包括温度、风速、风向、天气代码等信息。而hourly部分则包含了未来24小时每个小时的温度和天气代码。

通过API的响应结果，我们可以回答用户提出的问题：兰州今天天气。根据API的响应结果，兰州当前时间的温度为21.7°C，天气代码为3，表示有阵雨。同时，API还提供了未来24小时每个小时的温度和天气代码，用户可以根据这些信息了解兰州未来的天气情况。
[INFO][2023-05-12 14:57:08][tool_engine.py:193] - 我从[meteo-weather]中获得了一些信息：
'根据API的响应结果，我们可以看到兰州的经纬度信息以及当前时间的天气情况。其中，当前时间的天气情况包括温度、风速、风向、天气代码等信息。而hourly部分则包含了未来24小时每个小时的温度和天气代码。\n\n通过API的响应结果，我们可以回答用户提出的问题：兰州今天天气。根据API的响应结果，兰州当前时间的温度为21.7°C，天气代码为3，表示有阵雨。同时，API还提供了未来24小时每个小时的温度和天气代码，用户可以根据这些信息了解兰州未来的天气情况。'
[WARNING][2023-05-12 14:57:08][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.<locals>._completion_with_retry in 15.0 seconds as it raised RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-eMFYvNIDh2JEBVj3a4OMyQss on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method..

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

运行后报错

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

chatgpt-tool-hub version: 0.3.12
chatgpt-tool-hub 0.3.8后，部分工具名将变更：requests -> url-get
[INFO][2023-04-18 13:54:27][init.py:13] - [news] init failed, error_info: ModuleNotFoundError("No module named 'chatgpt_tool_hub.tools.morning_news'")
[INFO][2023-04-18 13:54:27][init.py:13] - [morning_news] init failed, error_info: ModuleNotFoundError("No module named 'chatgpt_tool_hub.tools.morning_news'")
[WARNING][2023-04-18 13:54:27][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[WARNING][2023-04-18 13:54:27][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[ERROR][2023-04-18 13:54:27][load_tools.py:46] - All the tools currently supported are：['url-get', 'bing-search', 'google-search', 'meteo-weather', 'python', 'terminal', 'wikipedia', 'wolfram-alpha']
[ERROR][2023-04-18 13:54:27][victorinox.py:35] - Got unknown tool: morning-news
Traceback (most recent call last):
File "/Users/Documents/chatgpt/chatgpt-tool-hub/chatgpt-tool-hub/chatgpt_tool_hub/apps/victorinox.py", line 33, in create
tools = load_tools(tools_list, **tools_kwargs)
File "/Users/Documents/chatgpt/chatgpt-tool-hub/chatgpt-tool-hub/chatgpt_tool_hub/tools/load_tools.py", line 47, in load_tools
raise ValueError(f"Got unknown tool: {name}")
ValueError: Got unknown tool: morning-news

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/Documents/chatgpt/chatgpt-tool-hub/chatgpt-tool-hub/test.py", line 18, in
app = AppFactory().create_app(tools_list=config["tools"], **config["kwargs"])
File "/Users/Documents/chatgpt/chatgpt-tool-hub/chatgpt-tool-hub/chatgpt_tool_hub/apps/app_factory.py", line 49, in create_app
app.create(tools_list, **kwargs)
File "/Users/Documents/chatgpt/chatgpt-tool-hub/chatgpt-tool-hub/chatgpt_tool_hub/apps/victorinox.py", line 36, in create
raise RuntimeError("tool初始化失败")
RuntimeError: tool初始化失败

tool工具在win下使用时，总是提示文件被占用导致失败

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

- [WX] receiveMsg=ChatMessage: id=6671363862168960699, create_time=1682256903, ctype=TEXT, content=$tool 搜索今日热点, from_user_id=wxid_k10fvreqzcbf22, from_user_nickname=梁爽, to_user_id=wxid_tt9en9ft8fhf29, to_user_nickname=格蕾修, other_user_id=wxid_k10fvreqzcbf22, other_user_nickname=梁爽, is_group=False, is_at=False, actual_user_id=None, actual_user_nickname=None, context=Context(type=TEXT, content=$tool 搜索今日热点, kwargs={'isgroup': False, 'msg': <channel.wechat.wechaty_message.WechatyMessage object at 0x000002A174536050>, 'origin_ctype': <ContextType.TEXT: 1>, 'session_id': 'wxid_k10fvreqzcbf22', 'receiver': 'wxid_k10fvreqzcbf22'})
[INFO][2023-04-23 21:35:04][victorinox.py:85] - 提问: 搜索今日热点
[INFO][2023-04-23 21:35:10][base.py:107] - 执行Tool: bing-search中...
[INFO][2023-04-23 21:35:10][bot.py:91] - 输入: 今日热点
[WARNING][2023-04-23 21:35:12][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[ERROR][2023-04-23 21:35:12][victorinox.py:88] - [APP] catch a Exception: [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'C:\\Users\\lhwyw\\AppData\\Local\\Temp\\tmpws2in_jq'
[INFO][2023-04-23 21:35:12][victorinox.py:85] - 提问: 搜索今日热点
[INFO][2023-04-23 21:35:19][base.py:107] - 执行Tool: bing-search中...
[INFO][2023-04-23 21:35:19][bot.py:91] - 输入: 今日热点
[WARNING][2023-04-23 21:35:21][chatgpt.py:171] - proxy no find, directly request to chatgpt instead
[ERROR][2023-04-23 21:35:21][victorinox.py:88] - [APP] catch a Exception: [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'C:\\Users\\lhwyw\\AppData\\Local\\Temp\\tmpl87ynly_'
[ERROR][2023-04-23 21:35:21][victorinox.py:92] - exceed retry_num
[ERROR][2023-04-23 21:35:21][tool.py:103] - 超过重试次数
Traceback (most recent call last):
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\apps\victorinox.py", line 86, in ask
    return self.bot.run(query)
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\chains\base.py", line 212, in run
    return self(args[0])[self.output_keys[0]]
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\chains\base.py", line 115, in __call__
    raise e
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\chains\base.py", line 112, in __call__
    outputs = self._call(inputs)
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\engine\tool_engine.py", line 158, in _call
    next_step_output = self._take_next_step(
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\engine\tool_engine.py", line 123, in _take_next_step
    observation = tool.run(
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\tools\base_tool.py", line 72, in run
    raise e

  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\tools\base_tool.py", line 69, in run
    observation = self._run(tool_input)
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\tools\bing_search\tool.py", line 28, in _run
    return self.api_wrapper.run(query)
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\tools\bing_search\wrapper.py", line 73, in run
    snippets.append(filter_text(result["snippet"]))
  File "C:\Python310\lib\site-packages\chatgpt_tool_hub\tools\web_requests\__init__.py", line 36, in filter_text
    os.remove(file_path)
PermissionError: [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'C:\\Users\\lhwyw\\AppData\\Local\\Temp\\tmpws2in_jq'

url-get和浏览器功能也是 有时会提示被占用，而占用的进程就是python.exe 就是他自己

python 3.10
windows11

关于代理配置问题

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [],
  "kwargs": {
      "debug": true  // debug模式一定要打开
  }
}

2. 你的问题：

我不需要代理，所以我在配置中将PROXY置为空，但是程序仍然使用了代理并且报错

3. 收到ai的回复：

4. debug模式终端打印的日志：

[INFO][2023-05-10 16:03:32][terminal_io.py:591] - > xxx: hi
[INFO][2023-05-10 16:03:32][victorinox.py:111] - xx: hi
[WARNING][2023-05-10 16:03:32][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.<locals>._completion_with_retry in 15.0 seconds as it raised APIConnectionError: Error communicating with OpenAI: Please check proxy URL. It is malformed and could be missing the host..

环境

• 操作系统类型 (Mac/Windows/Linux)：Mac
• Python版本 ( 执行 python -V )：Python 3.11.3
• pip版本 ( 执行 pip -V)：pip 18.1

回复时间过长，经常出现HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)

目前带有提示性使用tool，基本可以按照要求执行选择相应工具，但是经常链接api.openai.com超时，是由于请求超过频率了么。或者哪里使用不恰当，怎么使反应速度更快一点，亚马逊的机器和azure的机器都是这样！
日志记录如下：

[INFO][2023-04-08 01:58:36][SubscribeAccount.py:31] - [wechatmp] 162.62.81.123:36052 Receive post query ouhFW0hoT8cQC6k7HB9c3pJwNnSc 24064974339600504: $tool bing 查一下阿里公司的大模型
[INFO][2023-04-08 01:58:41][SubscribeAccount.py:31] - [wechatmp] 162.62.80.8:28940 Receive post query ouhFW0hoT8cQC6k7HB9c3pJwNnSc 24064974339600504: $tool bing 查一下阿里公司的大模型
[INFO][2023-04-08 01:58:46][SubscribeAccount.py:31] - [wechatmp] 162.62.80.57:50878 Receive post query ouhFW0hoT8cQC6k7HB9c3pJwNnSc 24064974339600504: $tool bing 查一下阿里公司的大模型
[WARNING][2023-04-08 01:58:48][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12).
[INFO][2023-04-08 01:58:50][SubscribeAccount.py:129] - [wechatmp] Three queries has finished For ouhFW0hoT8cQC6k7HB9c3pJwNnSc: 24064974339600504
[INFO][2023-04-08 01:58:56][base.py:99] - 执行Tool: Bing Search中...
[INFO][2023-04-08 01:58:56][bot.py:85] - 行动输入: 阿里公司大模型
[WARNING][2023-04-08 01:59:09][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12).
[WARNING][2023-04-08 01:59:25][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12).
[ERROR][2023-04-08 01:59:41][victorinox.py:87] - [APP] catch a Exception: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)
[INFO][2023-04-08 01:59:45][base.py:99] - 执行Tool: Bing Search中...
[INFO][2023-04-08 01:59:45][bot.py:85] - 行动输入: 阿里公司大模型
[WARNING][2023-04-08 01:59:57][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12).
[WARNING][2023-04-08 02:00:13][before_sleep.py:65] - Retrying chatgpt_tool_hub.models.chatgpt.chatgpt.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12).
[ERROR][2023-04-08 02:00:29][victorinox.py:87] - [APP] catch a Exception: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)
[ERROR][2023-04-08 02:00:29][victorinox.py:91] - exceed retry_num
[ERROR][2023-04-08 02:00:29][tool.py:92] - 超过重试次数
Traceback (most recent call last):
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 421, in _make_request
six.raise_from(e, None)
File "", line 3, in raise_from
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 416, in _make_request
httplib_response = conn.getresponse()
File "/usr/lib/python3.8/http/client.py", line 1348, in getresponse
response.begin()
File "/usr/lib/python3.8/http/client.py", line 316, in begin
version, status, reason = self._read_status()
File "/usr/lib/python3.8/http/client.py", line 277, in _read_status
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
File "/usr/lib/python3.8/socket.py", line 669, in readinto
return self._sock.recv_into(b)
File "/usr/lib/python3.8/ssl.py", line 1241, in recv_into
return self.read(nbytes, buffer)
File "/usr/lib/python3.8/ssl.py", line 1099, in read
return self._sslobj.read(len, buffer)
socket.timeout: The read operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/requests/adapters.py", line 489, in send
resp = conn.urlopen(
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 719, in urlopen
retries = retries.increment(
File "/usr/lib/python3/dist-packages/urllib3/util/retry.py", line 400, in increment
raise six.reraise(type(error), error, _stacktrace)
File "/usr/lib/python3/dist-packages/six.py", line 703, in reraise
raise value
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 665, in urlopen
httplib_response = self._make_request(
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 423, in _make_request
self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 330, in _raise_timeout
raise ReadTimeoutError(
urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 516, in request_raw
result = _thread_context.session.request(
File "/usr/local/lib/python3.8/dist-packages/requests/sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/requests/adapters.py", line 578, in send
raise ReadTimeout(e, request=request)
requests.exceptions.ReadTimeout: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 85, in ask
return self.bot.run(query)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 212, in run
return self(args[0])[self.output_keys[0]]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 155, in _call
next_step_output = self._take_next_step(
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot_executor.py", line 108, in _take_next_step
output = self.bot.plan(intermediate_steps, **inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot.py", line 115, in plan
action = self._get_next_action(full_inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/bots/bot.py", line 83, in _get_next_action
full_output = self.llm_chain.predict(**full_inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 151, in predict
return self(kwargs)[self.output_key]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 115, in call
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/base.py", line 112, in call
outputs = self._call(inputs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 57, in _call
return self.apply([inputs])[0]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 118, in apply
response = self.generate(input_list)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/chains/llm.py", line 62, in generate
return self.llm.generate_prompt(prompts, stop)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 78, in generate_prompt
raise e
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 75, in generate_prompt
output = self.generate(prompt_messages, stop=stop)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 52, in generate
results = [self._generate(m, stop=stop) for m in messages]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/base.py", line 52, in
results = [self._generate(m, stop=stop) for m in messages]
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 272, in _generate
response = self.completion_with_retry(messages=message_dicts, **params)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 234, in completion_with_retry
return _completion_with_retry(**kwargs)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 289, in wrapped_f
return self(f, *args, **kw)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 379, in call
do = self.iter(retry_state=retry_state)
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 325, in iter
raise retry_exc.reraise()
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 158, in reraise
raise self.last_attempt.result()
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 437, in result
return self.__get_result()
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 389, in __get_result
raise self._exception
File "/usr/local/lib/python3.8/dist-packages/tenacity/init.py", line 382, in call
result = fn(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/models/chatgpt/chatgpt.py", line 232, in _completion_with_retry
return self.client.create(**kwargs)
File "/usr/local/lib/python3.8/dist-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 216, in request
result = self.request_raw(
File "/usr/local/lib/python3.8/dist-packages/openai/api_requestor.py", line 527, in request_raw
raise error.Timeout("Request timed out: {}".format(e)) from e
openai.error.Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=12)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/wechat_mp/plugins/tool/tool.py", line 88, in on_handle_context
_reply = self.app.ask(query, user_session)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 89, in ask
return self.ask(query, chat_history, retry_num + 1)
File "/usr/local/lib/python3.8/dist-packages/chatgpt_tool_hub/apps/victorinox.py", line 92, in ask
raise TimeoutError("超过重试次数")
TimeoutError: 超过重试次数
[ERROR][2023-04-08 02:00:29][tool.py:93] - 超过重试次数
[INFO][2023-04-08 02:00:29][chat_gpt_bot.py:36] - [CHATGPT] query=请你随机用一种聊天风格，提醒用户：这个问题tool插件暂时无法处理

执行pip install chatgpt-tool-hub命令后应该怎么做

执行完之后我的chatgpt-on-wechat目录中并没有多出相应文件，我应该去哪修改配置

提议一个summary的prompts，现在的太高度总结，会错失一些内容

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

如题，提议prompts：

summarize the chat content in the document and answer in Chinese
Use the following format:
Sender name 1:<>

• <point_1>
  ..

Sender name 2:<>

• <point_1>
  ..

Sender name 3:<>

• <point_1>
  ..

Sender name 4:<>

• <point_1>
  ..

以上prompts在我索引本地聊天记录文档时，能得到良好的总结

tool调用设置问题

这段代码是加在 tool/config.json文档中么？

能说一下怎么在chatgpt-on-wechat项目上加google search吗

如题，我是小白，我把chatgpt-tool-hub项目里tool文件夹里的google_search文件复制到chatgpt-on-wechat项目里插件的文件夹里，配置了googlesearch的key和id，运行后，发送google search指令会报错，正确的操作方式应该是怎么样的

tool 插件运行 初始化失败

sample-chatgpt-on-wechat | chatgpt-tool-hub version: 0.3.14
sample-chatgpt-on-wechat | chatgpt-tool-hub 0.3.8后，部分工具名将变更：requests -> url-get
sample-chatgpt-on-wechat | [ERROR][2023-04-18 09:04:09][plugin_manager.py:110] - Failed to import plugin tool: No module named 'webdriver_manager'
sample-chatgpt-on-wechat | Traceback (most recent call last):
sample-chatgpt-on-wechat | File "/app/plugins/plugin_manager.py", line 105, in scan_plugins
sample-chatgpt-on-wechat | self.loaded[plugin_path] = importlib.import_module(
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/importlib/init.py", line 126, in import_module
sample-chatgpt-on-wechat | return _bootstrap._gcd_import(name[level:], package, level)
sample-chatgpt-on-wechat | File "", line 1050, in _gcd_import
sample-chatgpt-on-wechat | File "", line 1027, in _find_and_load
sample-chatgpt-on-wechat | File "", line 1006, in _find_and_load_unlocked
sample-chatgpt-on-wechat | File "", line 688, in _load_unlocked
sample-chatgpt-on-wechat | File "", line 883, in exec_module
sample-chatgpt-on-wechat | File "", line 241, in _call_with_frames_removed
sample-chatgpt-on-wechat | File "/app/plugins/tool/init.py", line 1, in
sample-chatgpt-on-wechat | from .tool import *
sample-chatgpt-on-wechat | File "/app/plugins/tool/tool.py", line 4, in
sample-chatgpt-on-wechat | from chatgpt_tool_hub.apps import load_app
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/site-packages/chatgpt_tool_hub/apps/init.py", line 1, in
sample-chatgpt-on-wechat | from chatgpt_tool_hub.apps.load_app import load_app
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/site-packages/chatgpt_tool_hub/apps/load_app.py", line 7, in
sample-chatgpt-on-wechat | from chatgpt_tool_hub.tools import dynamic_tool_loader
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/site-packages/chatgpt_tool_hub/tools/init.py", line 5, in
sample-chatgpt-on-wechat | from chatgpt_tool_hub.tools.web_requests.browser import BrowserTool
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/site-packages/chatgpt_tool_hub/tools/web_requests/init.py", line 42, in
sample-chatgpt-on-wechat | from chatgpt_tool_hub.tools.web_requests.wrapper import RequestsWrapper
sample-chatgpt-on-wechat | File "/usr/local/lib/python3.10/site-packages/chatgpt_tool_hub/tools/web_requests/wrapper.py", line 11, in
sample-chatgpt-on-wechat | from webdriver_manager.chrome import ChromeDriverManager
sample-chatgpt-on-wechat | ModuleNotFoundError: No module named 'webdriver_manager'

Tool插件-报错“超过重试次数”-星球提问

前置确认

1. 网络能够访问openai接口 ——能

2. git pull 拉取最新代码 ——是最新的代码

3. 执行pip install -r requirements.txt，检查依赖是否满足 ——安装chatgpt-tool-hub-master内的依赖，报错：

WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))': /simple/setuptools/ 更换了很多节点，还是不行。但是chatgpt-on-wechat内的依赖都安装过了。

4. 在已有 issue 中未搜索到类似问题 ——和#14问题有点类似，但是我询问过lanvent后，得到的问题是：prxy error，该链接是：/v1/forecast?latitude=%7Blatitude%7D&longitude=%7Blongitude%7D&hourly=temperature_2m,rain&current_weather=true&timezone=auto&start_date=%7Btoday's%20date%7D&end_date=%7Btoday's%20date%7D

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？
在test.py中复现：最终报错还是“超过重试次数”，出错的代码是：
`[INFO][2023-04-16 20:15:41][__init__.py:13] - [news] init failed, error_
gpt_tool_hub.tools.news.api_docs_prompts'")
[INFO][2023-04-16 20:15:41][__init__.py:13] - [morning_news] init failed
ed 'chatgpt_tool_hub.tools.morning_news'")
[WARNING][2023-04-16 20:15:41][chatgpt.py:171] - proxy no find, directly
[WARNING][2023-04-16 20:15:41][chatgpt.py:171] - proxy no find, directly
[INFO][2023-04-16 20:15:41][victorinox.py:39] - Initializing Victorinox
al', 'meteo-weather'], params: {'openai_api_key': '': False, 'request_timeout': 60, 'no_default': False, 'model_name':
[WARNING][2023-04-16 20:15:41][before_sleep.py:65] - Retrying chatgpt_to
ion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it rais
OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retrie
d by ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))).
[ERROR][2023-04-16 20:15:45][victorinox.py:86] - [APP] catch a Exception
onPool(host='api.openai.com', port=443): Max retries exceeded with url:
ot connect to proxy.', OSError(0, 'Error')))
[WARNING][2023-04-16 20:15:45][before_sleep.py:65] - Retrying chatgpt_to
ion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it rais
OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retrie
d by ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))).`


1. 你复现时的config.json，**注意抹去你的api-key**
``{
  "tools": [],
  "kwargs": {
      "openai_api_key": "",
      "proxy": "",     //是本地windows环境运行，用了clash的代理
      "debug": false,
      "request_timeout": 60,
      "no_default": false,
      "model_name": "gpt-3.5-turbo"
  }
}

2. 你的问题：

[我部署的微信个人版本的，在配置完json文件后，向机器人输入$tool 给我今天的早报 后，后台cmd返还的是：超过重试次数。
错误的代码是：
ERROR][2023-04-14 23:04:11][victorinox.py:87] - [APP] catch a Exception: HTTPSConnectionPool(host='api.open-meteo.com', port=443): Max retries exceeded with url: /v1/forecast?latitude=%7Blatitude%7D&longitude=%7Blongitude%7D&hourly=temperature_2m,rain&current_weather=true&timezone=auto&start_date=%7Btoday's%20date%7D&end_date=%7Btoday's%20date%7D (Caused by ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))) [INFO][2023-04-14 23:04:13][base.py:99] - 执行Tool: Meteo Weather中... [INFO][2023-04-14 23:04:13][bot.py:87] - 行动输入: 今天的天气怎么样？ [ERROR][2023-04-14 23:04:16][victorinox.py:87] - [APP] catch a Exception: HTTPSConnectionPool(host='api.open-meteo.com', port=443): Max retries exceeded with url: /v1/forecast?latitude=%7Blatitude%7D&longitude=%7Blongitude%7D&hourly=temperature_2m,rain&current_weather=true&timezone=auto&start_date=%7Btoday's%20date%7D&end_date=%7Btoday's%20date%7D (Caused by ProxyError('Cannot connect to proxy.', OSError(0, 'Error'))) [ERROR][2023-04-14 23:04:16][victorinox.py:91] - exceed retry_num [ERROR][2023-04-14 23:04:16][tool.py:92] - 超过重试次数
在需求帮助后，得到的回复是 proxy error 。
我的json 代码是：
{ "tools": ["python", "url-get", "terminal", "meteo-weather", "bing-search", "morning-news"], "kwargs": { "openai_api_key": "xxxxx", "top_k_results": 2, "no_default": false, "model_name": "gpt-3.5-turbo", "bing_subscription_key":"xxxx", "zaobao_api_key": "xxxx" } }

本地电脑使用代理工具为 clash。尝试了多个代理IP，均是上述问题。
]

3. 收到ai的回复：

[Hi，您好！很高兴能为您服务。抱歉，我们的tool插件现在可能还不能回答您的问题。我们一直在努力优化我们的AI服务，但在某些情况下，它可能无法提供满意的答案。

我们肯定会将您的反馈传递给我们的团队，并尽快完善我们的技术。感谢您对ChatGPT的支持和理解。

如果您有其他问题或者需要我们为您做些什么，请随时告诉我们，我们会竭尽所能为您服务。]

4. debug模式终端打印的日志：
   这个操作我不会

环境

• 操作系统类型 (Mac/Windows/Linux)：Windows
• Python版本 ( 执行 python -V )：3.8.2
• pip版本 ( 执行 pip -V)：23.0.1

news初始化失败，添加news-api tool及morning-news tool时失败

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": ["news", "python", "terminal", "url-get", "meteo-weather"],
  "kwargs": {
      "debug": true,
      "no_default": false,
      "news_api_key": "0b3ed",
      "morning_news_api_key": "IbU",
      "nolog": true,
      "human_prefix": "user"
  }
}

2. 你的问题：
3. 收到ai的回复：
4. debug模式终端打印的日志：
   
   

环境

• 操作系统类型 ：Windows
• Python版本 ( 执行 python -V )： 3.11.2
• pip版本 ( 执行 pip -V)：23.1.2

使用python脚本执行出现依赖问题

你好，我这边在个人号接入之后，脚本是需要更新相关依赖的，所以当我执行 bot $tool 执行 "python3 /root/download.py 40735"会出现错误，提示：[Terminal] Command 'python3 /root/download.py 40735' returned non-zero exit status 1.请问这里的python是调用哪里的服务？我直接在控制台执行脚本是可以跑的。

wikipedia出错

bot $tool 使用工具wikipedia 查找：小红帽

[bot] the response to the original input question in chineseThought: Do I need to use a tool? Yes
Action: requests_get, "https://zh.wikipedia.org/wiki/%E5%B0%8F%E7%BA%A2%E5%B8%BD"

能够增加一个支持图片文字识别的功能吗？就是我发送图片后，能够识别文字，然后回复我。

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

0. 你的问题是否在test.py能复现？

1. 你复现时的config.json，注意抹去你的api-key

{
  "tools": [],
  "kwargs": {
      "debug": true  // debug模式一定要打开
  }
}

2. 你的问题：

[替换我]

3. 收到ai的回复：

[替换我]

4. debug模式终端打印的日志：

[替换我]

环境

• 操作系统类型 (Mac/Windows/Linux)：
• Python版本 ( 执行 python -V )：
• pip版本 ( 执行 pip -V)：

关于在chatgpt-on-wechat上使用出现的一些问题

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

我使用这个工具来搜索一些信息时，返回的结果并不是这个信息的内容，而一直都是问我还是否需要一些帮助。
在此举个例子,我在微信中询问关于克劳德莫奈的信息，而返回的结果如下。

但是很明显，用户需要获取的信息
并不是这个，

比起这个回答，更应该返回的是终端里的总结信息。
而且如果继续提问，很容易陷入这样的循环......在这个问题中我并不知道关于克劳德莫奈的哪些生平信息，但它却还在反问我想知道哪些信息。

另外，我发现使用的过程中反刍的次数太多了，对于同一个问题明明第一次提问已经得到了答案，却还要继续反思然后继续重复问题来得到结果，这样十分消耗token。更重要的事，在反刍的过程中，直接显示：[APP] catch a Exception: This model's maximum context length is 4097 tokens. However, your messages resulted in 11227 tokens. Please reduce the length of the messages.超出了最大token限制了....然后直接报错，白白浪费了我的token。

无法安装 chatgpt-tool-hub，输出setuptools>=40.8.0 错误

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

5. 注意，提issue前请确认用本项目test.py(参考README.md 快速开始配置)重试一次你的问题是否能复现

问题描述

无法安装依赖。
执行：

pip install -i https://pypi.python.org/simple chatgpt-tool-hub --proxy=127.0.0.1:7890

总是输出：
【 ERROR: Could not find a version that satisfies the requirement setuptools>=40.8.0 (from versions: none)】

实际上已经安装了的：

pip list|findstr "setup"
setuptools 67.7.2 （改为40.8.0 后重试上一操作，依然如此）

环境

• 操作系统类型 (Mac/Windows/Linux)：win11 x64
• Python版本 ( 执行 python -V )： 3.8.9
• pip版本 ( 执行 pip -V)：23.1.2

大佬求教，配置news的api不成功

前置确认

1. 网络能够访问openai接口

2. git pull 拉取最新代码

3. 执行pip install -r requirements.txt，检查依赖是否满足

4. 在已有 issue 中未搜索到类似问题

求教各位大佬，news配置一直不成功，相关配置文件和返回结果如下，求教！

config.json文件如下：
{
"tools": ["python", "url-get", "terminal", "meteo-weather", "wikipedia", "bing-search", "news", "morning-news" ],
"kwargs": {
"debug": true,
"request_timeout": 120,
"no_default": false,
"bing_subscription_key": "5779454a6axxxxxd4d4b8e3270",
"news_api_key": "e8932ac5b3xxxxxx706c4aff8aa5061",
"morning_news_api_key": "lyI2xxxxxpJ5jW"
}
}

后台报错链接如下：https://newsapi.org/v2/top-headlines?pageSize=2&page=1
打开链接后结果如下：{"status":"error","code":"apiKeyMissing","message":"Your API key is missing. Append this to the URL with the apiKey param, or use the x-api-key HTTP header."}

使用bing-search时报错

[INFO][2023-04-10 11:08:29][base.py:99] - 执行Tool: requests_get中...
[INFO][2023-04-10 11:08:29][bot.py:87] - 行动输入: https://cn.bing.com/search?q=大连市明天天气

[ERROR][2023-04-10 11:08:30][get.py:23] - [requests_get] Couldn't find a tree builder with the features you requested: lxml. Do you need to install a parser library?
[INFO][2023-04-10 11:08:32][bot.py:87] - 行动输入: None
[INFO][2023-04-10 11:08:35][wechat_channel.py:164] - [WX] sendMsg=Reply(type=TEXT, content=the response to the original input question in chineseThought: Do I need to use a tool? Yes
Action: requests_get
Action Input: https://cn.bing.com/search?q=大连市明天天气), receiver=@be7690216d93f53e4f0911cf496de7291daee41b5ad11111e6557bd24f01d8a0

我的config.json.template:
{
"tools": ["python", "requests", "terminal", "meteo-weather", "bing-search"],
"kwargs": {
"top_k_results": 2,
"no_default": false,
"model_name": "gpt-3.5-turbo",
"bing_subscription_key": "0db7b530e38b40a5a6b65a94dd79e9"
}
}

能否调用httpchatgpt

想问问代码对于chatgptapi的某些接口依赖非常高吗，是否可以采用revChatGPT.V1替换