<html>
<head>
<base href="https://bugzilla.suse.com/" />
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_REOPENED "
title="REOPENED - Cannot add content to Open WebUI knowledge base"
href="https://bugzilla.suse.com/show_bug.cgi?id=1234244#c10">Comment # 10</a>
on <a class="bz_bug_link
bz_status_REOPENED "
title="REOPENED - Cannot add content to Open WebUI knowledge base"
href="https://bugzilla.suse.com/show_bug.cgi?id=1234244">bug 1234244</a>
from <span class="vcard"><span class="fn">Meera Belur</span>
</span></b>
<pre>The "Add text" issue was due to missing NLTK datasets. We have introduced a new
environment variable INSTALL_NLTK_DATASETS that enables the customer to install
the NLTK datasets. By setting this to "true", the NLTK datasets will be
installed.
Please add this to the documentation:
Issue: "Add text" RAG functionality produces an error 'Extracted content is not
available for this file. Please ensure that the file is processed before
proceeding.'
Fix: Customer has to supply an additional extraEnvVars INSTALL_NLTK_DATASETS
and set it to "true". Customer is encouraged to read through the licensing of
NLTK datasets at <a href="https://github.com/nltk/nltk/blob/develop/README.md">https://github.com/nltk/nltk/blob/develop/README.md</a>
- name: INSTALL_NLTK_DATASETS
value: "true"</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the QA Contact for the bug.</li>
</ul>
</body>
</html>