KwaiKEG / KwaiAgents

A generalized information-seeking agent system with Large Language Models (LLMs).
Other
1.09k stars 105 forks source link

web_search无法使用 #17

Open ZzzIKnow opened 10 months ago

ZzzIKnow commented 10 months ago

Traceback (most recent call last): File "c:\users\user\desktop\kwaiagents-main\kwaiagents-main\kwaiagents\tools\search.py", line 119, in _retry_search_result if not search_results and counter >= 2: ^^^^^^^^^^^^^^ UnboundLocalError: cannot access local variable 'search_results' where it is not associated with a value

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "c:\users\user\desktop\kwaiagents-main\kwaiagents-main\kwaiagents\tools\search.py", line 119, in _retry_search_result if not search_results and counter >= 2: ^^^^^^^^^^^^^^ UnboundLocalError: cannot access local variable 'search_results' where it is not associated with a value

ScarletPan commented 10 months ago

请问可以在 kwaiagents/tools/search.py 下加入下列代码,然后单独运行一下kwaiagents/tools/search.py吗?

if __name__ == "__main__":
    search_tool = SearchTool()
    print(search_tool("刘德华老婆"))
ZzzIKnow commented 10 months ago

Traceback (most recent call last): File "C:\Users\User\Desktop\KwaiAgents-main\KwaiAgents-main\kwaiagents\tools\search.py", line 115, in _retry_search_result search_results = self.get_results_by_ddg(keyword) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\User\Desktop\KwaiAgents-main\KwaiAgents-main\kwaiagents\tools\search.py", line 99, in get_results_by_ddg for r in islice(ddgs_gen, self.max_search_nums): File "D:\Anaconda\envs\RAG\Lib\site-packages\duckduckgo_search\duckduckgo_search.py", line 91, in text for i, result in enumerate(results, start=1): File "D:\Anaconda\envs\RAG\Lib\site-packages\duckduckgo_search\duckduckgo_search.py", line 119, in _text_api vqd = self._get_vqd(keywords) ^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Anaconda\envs\RAG\Lib\site-packages\duckduckgo_search\duckduckgo_search.py", line 54, in _get_vqd resp = self._get_url("POST", "https://duckduckgo.com", data={"q": keywords}) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Anaconda\envs\RAG\Lib\site-packages\duckduckgo_search\duckduckgo_search.py", line 50, in _get_url raise DuckDuckGoSearchException(f"_get_url() {url} {type(ex).name}: {ex}") duckduckgo_search.exceptions.DuckDuckGoSearchException: _get_url() https://duckduckgo.com RequestsError: Failed to perform, ErrCode: 28, Reason: 'Failed to connect to duckduckgo.com port 443 after 21034 ms: Timed out'. This may be a libcurl error, See https://curl.se/libcurl/c/libcurl-errors.html first for more details.

Traceback (most recent call last): File "C:\Users\User\Desktop\KwaiAgents-main\KwaiAgents-main\kwaiagents\tools\search.py", line 119, in _retry_search_result if not search_results and counter >= 2: ^^^^^^^^^^^^^^ UnboundLocalError: cannot access local variable 'search_results' where it is not associated with a value

ZzzIKnow commented 10 months ago

我这网址是可以访问的,在工具类下也不能使用

ScarletPan commented 10 months ago

Hi 你在命令行代理开了不,终端里直接curl https://api.duckduckgo.com/能有返回吗

sudoskys commented 9 months ago

duckduckgo_search 库为逆向库,需要实时跟进版本,请运行 pip -U duckduckgo_search 升级依赖

ZzzIKnow commented 9 months ago

Hi 你在命令行代理开了不,终端里直接curl https://api.duckduckgo.com/能有返回吗

需要在命令行中开代理嘛

ScarletPan commented 9 months ago

需要的,指定 http_proxy

ZzzIKnow commented 9 months ago

还是原来的问题 代理开了的情况下

image image

ScarletPan commented 9 months ago

重新刷一下dns缓存看看是否可以么?curl一下主网站呢? curl https://duckduckgo.com/