{"id":14112,"date":"2026-11-17T11:02:54","date_gmt":"2026-11-17T02:02:54","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=14112"},"modified":"2026-11-17T11:12:14","modified_gmt":"2026-11-17T02:12:14","slug":"open-webui-v0125-released","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0125-released\/","title":{"rendered":"Open WebUI v0.12.5 Released with Security Patches and Multi-Page Notes"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/github.com\/open-webui\/open-webui\">open-webui\/open-webui<\/a><\/td>\n<\/tr>\n<tr>\n<td>Version<\/td>\n<td><a href=\"https:\/\/github.com\/open-webui\/open-webui\/releases\/tag\/v0.12.5\">v0.12.5<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-29<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>NOASSERTION<\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>Open WebUI v0.12.5 has been released. Open WebUI is a user-friendly, Python-based AI interface that supports Ollama, the OpenAI API, and other backends.<\/p>\n<p>This version includes important security fixes, and the development team strongly recommends updating as soon as possible across all environments. In terms of features, numerous changes have been made to improve usability and performance, such as multi-page support for notes, expanded administrator analytics, and up to 10x faster knowledge base searches.<\/p>\n<h2>Key Changes<\/h2>\n<h3>Security Vulnerability Fixes and Update Recommendation<\/h3>\n<p>This release includes important security fixes. Prompt updates are strongly recommended for all deployments to ensure secure operation. Detailed advisories regarding individual vulnerabilities are scheduled to be published as soon as CVE assignments are complete. Administrators should update to the latest version immediately.<\/p>\n<h3>Multi-Page Support and Live Presence in Notes<\/h3>\n<p>The notes feature has been expanded to allow the creation of multiple pages and sub-pages within a single note. Page tabs allow users to add, rename, reorder, delete, and link to pages, with models and search functions operating on a per-page basis. Additionally, a &#8220;Live presence&#8221; feature has been implemented, allowing users to see in real-time which page and position other users are working on within a note.<\/p>\n<h3>Enhanced Administrator Features (Session Inspection and API Key Management)<\/h3>\n<p>A &#8220;Sessions&#8221; tab has been added to the administrator analytics. When the environment variable <code>ENABLE_ADMIN_CHAT_ACCESS<\/code> is enabled, administrators can list token counts, response contents, errors, and processing times for each chat, filtered by model and token range. Furthermore, individual API keys can now be rotated or deleted from the user edit dialog.<\/p>\n<h3>Faster Knowledge Base Processing and Search<\/h3>\n<p>Various knowledge base commands (<code>ls<\/code>, <code>cat<\/code>, <code>grep<\/code>) and synchronization checks have been improved to retrieve lists without reading the full text of each file. This increases call speeds by up to 10x in large knowledge bases and significantly reduces memory consumption. In addition, embedding processing for large documents now defaults to batch processing in increments of 1,000 chunks (configurable via the <code>RAG_EMBEDDING_BUFFER_SIZE<\/code> environment variable), greatly reducing memory load.<\/p>\n<h3>Improved Chat Screen Usability and Input Bug Fixes<\/h3>\n<p>Chats can now be renamed directly from the menu next to the open chat title. For chats within folders owned by the user, titles can be changed even if created by another user. Additionally, a bug (present since v0.12.4) has been fixed where pressing the Backspace key during Japanese or other IME text input would commit the text or cause it to display redundantly.<\/p>\n<h3>Support for ComfyUI Animated Images and Metrics Exclusion Settings<\/h3>\n<p>Images generated from ComfyUI&#8217;s &#8220;Save Animated WEBP&#8221; and &#8220;Save Animated PNG&#8221; nodes are now displayed in animated format on the chat screen. Also, in OpenTelemetry metrics, specifying <code>OTEL_PYTHON_FASTAPI_EXCLUDED_URLS<\/code> or <code>OTEL_PYTHON_EXCLUDED_URLS<\/code> now allows health check requests like <code>\/health<\/code> to be excluded from metrics measurement.<\/p>\n<h2>Hardware Requirements<\/h2>\n<p>This version improves the flexibility of integrating external models and configuring various embedding and optical character recognition models.<\/p>\n<ul>\n<li>\n<p><strong>Mistral OCR Model Selection and Custom Parameter Settings<\/strong><br \/>\n  The <code>Admin Settings &gt; Documents<\/code> management screen and the <code>MISTRAL_OCR_PARAMS<\/code> environment variable can now be used to specify the Mistral OCR model to use or send additional request options. This allows flexible handling of older OCR model versions or parameter settings required by Azure AI Foundry endpoints.<\/p>\n<\/li>\n<li>\n<p><strong>Improved Support for Kokoro.js (Browser Audio Model)<\/strong><br \/>\n  When selecting &#8220;Kokoro.js (Browser)&#8221; in audio settings (<code>Settings &gt; Audio<\/code>), a bug was fixed where the Read Aloud function would not correctly speak using the selected Kokoro voice.<\/p>\n<\/li>\n<li>\n<p><strong>UI Settings for Embedding Model Prefixes<\/strong><br \/>\n  Query prefixes (<code>RAG_EMBEDDING_QUERY_PREFIX<\/code>) and content prefixes (<code>RAG_EMBEDDING_CONTENT_PREFIX<\/code>) required by certain embedding models can now be configured directly from the <code>Admin Settings &gt; Documents<\/code> management screen, in addition to the traditional environment variable configuration.<\/p>\n<\/li>\n<li>\n<p><strong>Support for Reranker Models Returning Negative Scores<\/strong><br \/>\n  When using reranker models that return raw scores below 0, negative values can now be entered into the Relevance Threshold field under <code>Admin Settings &gt; Documents<\/code>.<\/p>\n<\/li>\n<li>\n<p><strong>Nvidia GPU \/ CUDA Acceleration<\/strong><br \/>\n  In Docker environments, acceleration using Nvidia GPUs is available by using CUDA-enabled images (<code>ghcr.io\/open-webui\/open-webui:cuda<\/code>) or GPU flags.<\/p>\n<\/li>\n<\/ul>\n<h2>How to Get It<\/h2>\n<p>Open WebUI installation and updates are performed using Python pip or Docker. Follow the steps below according to your existing environment.<\/p>\n<h3>Python pip Updates and Installation<\/h3>\n<p>To avoid compatibility issues, <strong>Python 3.12<\/strong> is recommended.<\/p>\n<ol>\n<li>Install or update the package:<\/li>\n<\/ol>\n<pre><code class=\"language-bash\">pip install open-webui\n<\/code><\/pre>\n<ol start=\"2\">\n<li>Start the server:<\/li>\n<\/ol>\n<pre><code class=\"language-bash\">open-webui serve\n<\/code><\/pre>\n<p>After starting, access <code>http:\/\/localhost:8080<\/code> in your browser to use it.<\/p>\n<h3>Docker Updates and Installation<\/h3>\n<p>When operating with Docker, be sure to run the container with the data mount option <code>-v open-webui:\/app\/backend\/data<\/code> specified to prevent data loss.<\/p>\n<ul>\n<li><strong>When Ollama is running on the same machine<\/strong><\/li>\n<\/ul>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:main\n<\/code><\/pre>\n<ul>\n<li><strong>When Ollama is running on another server<\/strong><br \/>\nSpecify the target server&#8217;s URL in <code>OLLAMA_BASE_URL<\/code>.<\/li>\n<\/ul>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https:\/\/example.com -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:main\n<\/code><\/pre>\n<ul>\n<li><strong>When using Nvidia GPU (CUDA)<\/strong><br \/>\nInstall the Nvidia CUDA container toolkit on your Linux or WSL environment beforehand, then run:<\/li>\n<\/ul>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:cuda\n<\/code><\/pre>\n<ul>\n<li><strong>When using only the OpenAI API<\/strong><\/li>\n<\/ul>\n<pre><code class=\"language-bash\">docker run -d -p 3000:8080 -e OPENAI_API_KEY=your_secret_key -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:main\n<\/code><\/pre>\n<ul>\n<li><strong>When using the bundled image containing both Open WebUI and Ollama<\/strong><\/li>\n<li><strong>With GPU support:<\/strong> <code>bash docker run -d -p 3000:8080 --gpus=all -v ollama:\/root\/.ollama -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:ollama<\/code> &#8211; <strong>CPU only:<\/strong> <code>bash docker run -d -p 3000:8080 -v ollama:\/root\/.ollama -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:ollama<\/code><\/li>\n<\/ul>\n<p>When started via Docker, access <code>http:\/\/localhost:3000<\/code>.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0-13-0\/\">Open WebUI v0.13.0 Released: Tabbed Workspaces &amp; Security Fixes<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0-12-0\/\">Open WebUI v0.12.0 Released: Real-Time Voice &amp; VRM Avatars<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/22\/open-webui-v0-11-4\/\">Open WebUI v0.11.4 Released: Dramatic Docker Image Slimming<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/open-webui-v0131-release\/\">Open WebUI v0.13.1 Released with Security Fixes and Tether<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Follow this tool<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-open-webui-en\/\">Open WebUI overview and release history (181 releases tracked)<\/a><\/li>\n<li><strong>Other uis and desktop apps<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-jan-en\/\">Jan<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-text-generation-webui-en\/\">TextGen<\/a><\/li>\n<li><strong>Engines mentioned in this article<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/releases\/tag\/v0.12.5\">open-webui\/open-webui v0.12.5 Release Notes<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/33177\">Pull Request #33177: feat: rename a chat from the menu next to its title<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/33339\">Pull Request #33339: fix: folder owners can rename another user&#8217;s chat from the menu next to its title<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/33329\">Pull Request #33329: feat: let admins exclude routes like health checks from OpenTelemetry metrics<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/open-webui\/open-webui\/pull\/33183\">Pull Request #33183: fix: the search window only offers locations that fit the chosen content type<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Open WebUI v0.12.5 is now available, featuring important security fixes, multi-page notes, faster knowledge base searches, and various UI improvements.<\/p>\n","protected":false},"author":1,"featured_media":14111,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[105],"tags":[1475,1093,1917,590,4345,1547],"class_list":["post-14112","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-engines-and-tools","tag-docker-en","tag-ollama-en","tag-open-webui-en","tag-python-en","tag-rag-en","tag-verified"],"lang":"en","translations":{"en":14112,"ja":14110},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/14112","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=14112"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/14112\/revisions"}],"predecessor-version":[{"id":17990,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/14112\/revisions\/17990"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/14111"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=14112"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=14112"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=14112"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}