add to qwen reading list

[jmanhype]

not working everytime i add i get this error IndexError: list index out of range

the inference works beteween qwen but its not able to add to reading list or read the list

HELP

[JianxinMa]

@tuhahaha Let's discuss how we can address this issue when you return from your vacation.

A little more background on the cause of this issue:

When a user clicks the Add button, (1) the URL is saved to a temporary file, and (2) the chatbot will look at that temporary file. The current implementation assumes that Step 1 finishes before Step 2 starts. However, this doesn't always seem to be the case. For example, what if Step 1 is blocked by some other operation? What if the write operation fails? In such scenarios, Step 2 will fail with an IndexError: list index out of range.

[JianxinMa]

I suspect that the frequent cause of this issue is either one of the following:

• (More likely) The user is clicking the Add button while having the popup page open. This can lead to a race condition. We need to add some precautions to prevent this.
• (Less likely) We are having a permission issue when dealing with that temporary file. Perhaps even the directory is not created properly.

[JianxinMa]

Oh, this is a different issue, not the same one that I am talking about in my previous comment. The IndexError occurs when executing te following code:

...
data['content'] = parse_html_bs(...)  # Using bs4 inside to parse html content received from the chrome extension.
...
extract = data['content'][0]['metadata']['title']  # Here!

@tuhahaha It looks like bs4 fails to retrieve the content of the page here. I'm still trying to reproduce this issue and figure out why it occurs.

@tuhahaha Btw, we need to automatically detect the language and use English prompts when dealing with English requests.

[JianxinMa]

I just pushed a quick fix. Please pull the latest code and see if it works for you.

Details:

• I managed to reproduce the issue on a Windows machine. WSL2 works fine, but native Windows does not.
• On my machine, this is related to the str codec, which is a mess on Windows since it does not always use UTF-8 and may instead use other encodings such as GBK or Latin-1.