When a message mixed right-to-left and left-to-right lines, the chat input and the sent message gave every line the direction of the first one, so an English line under an Arabic one showed up as "?Hello, how are you" with the question mark at the start and sat on the wrong side. Each line now picks its own direction and alignment, both while typing and in the sent message. With Chat Direction set to LTR or RTL instead of Auto, lines in the input box now also align by their own language, the way sent messages already did.
Fixes#31827
With All time selected, the Daily Messages chart in Admin Panel > Analytics failed to load (the daily analytics request returned a 500) as soon as one message had been saved without a timestamp, for example a chat created through the API with a null timestamp. A date range still worked because those messages were left out of it. Such messages now get the time they were saved, and ones already stored without a timestamp are counted on today's date instead of breaking the chart. Messages that came after the missing timestamp in the same chat were also left out of analytics before and are now counted.
Fixes#27316
With Rich Text Input for Chat on, pasting an HTML email or newsletter into the chat input looked fine, but the sent message repeated the same text over and over as Markdown table rows. These emails are laid out with tables nested inside other tables, and the content of each inner table was counted again for every table around it. Pasted content is now sent once, and regular tables are unaffected.
Fixes#24657
Lines separated by a single newline show on separate lines while you chat, but after reloading the page or opening a chat by its URL they run together into one line, and on shared chat links they always did. The single-newline line break setting was only switched on once the chat input had loaded, so any message shown before that rendered without it. It is now on from the start, so messages look the same after a reload, from a URL and on shared links as they do while chatting.
With the Web API speech-to-text engine, the two-second silence timer only restarted when the browser finished a phrase. If you paused briefly and then kept talking for more than two seconds, dictation stopped mid-sentence. The timer now restarts whenever the browser hears speech, so dictation only stops after two seconds of silence.
Fixes#19727
Saving an edited reply stored the new structured output but set the message's plain content to an empty string. Chat search only matches message content, so the chat could no longer be found by the edited text, nor by the text it replaced.
editMessage now fills content from the edited output with the existing getOutputText, the same text the reply is shown with. Saving as a copy does the same. Output still takes precedence for rendering and for the next request to the model, so only the searchable copy changes.
Fixes#31471
Co-authored-by: RaulMermans <214883465+RaulMermans@users.noreply.github.com>
In chat replies, inline math written right next to an em dash or en dash, with either $...$ or \(...\), was left unrendered, as in "constants—\(e\), \(i\) and \(0\)—in one equation" where the 0 showed up as plain "(0)". Both dashes are now allowed directly before or after a formula, like spaces, commas and brackets already are, so the math renders whenever a dash touches it.
Images stored inside the chat record itself (chats from older versions, images that could not be saved as files, temporary chats) had their encoded data counted as text when estimating how full the context is, so a single 3 MB image counted as about a million tokens. That pushed the chat over the compaction threshold, summarizing older messages while the chat was well under the limit, and made the context usage indicator jump. The encoded image data is now left out of the token estimate, both for compaction and for the indicator.
Fixes#31913
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Translate empty and missing Japanese UI strings, including plural forms that Japanese does not distinguish, and correct a few existing labels.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
When a reply was stopped or failed before the model sent any text, the chat kept an empty reply, and every later message in that chat sent it back to the model as part of the conversation. Providers that reject empty assistant messages then refused every new request, so the chat stayed unusable unless the empty reply was deleted from the database by hand. Empty replies are now skipped when the conversation is sent to the model, as replies that ended in an error already were. Chats already stuck like this work again on their next message, since nothing stored has to change.
Fixes#25083
Pasting a large block of text (around 150 KB or more) into a note made the note's live connection drop and reconnect, and the text was never saved, so a reload showed the note without it. Each edit message carries the whole note in several formats, which pushed it past the server's 1 MB cap on a single message. That cap is now 16 MiB, the same size the server already accepts for a websocket message, so notes with up to about 2 MB of text save again.
Fixes#26140
Connecting an MCP tool server over OAuth 2.1 failed after signing in at the provider with an "invalid or expired state" error whenever the server advertises a long list of scopes, such as the Google Workspace MCP server with its 42 Google scopes. Open WebUI saved the full authorization link it sends to the provider in the session cookie, which pushed the cookie past the 4096-byte browser limit, so the browser dropped it and Open WebUI could not recognise the user when the provider sent them back. The link is no longer saved there, so the cookie stays at a few hundred bytes even with long scope lists.
Fixes#26382
Opening a chat only cleared the loading cursor on the newest response that never finished, so an older one (from a cancelled generation, or a turn an earlier Open WebUI version left unfinished) kept spinning and never showed its copy and regenerate buttons. Now, when no generation is running in the chat, every unfinished response shows as finished on load, except one waiting for the user to answer a tool's question. While a generation is running nothing changes, because another model's response to the same message may still be streaming in.
Fixes#14806
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Some providers, such as OpenVINO Model Server, number their output items from zero again in every response. When a model wrote text, called a tool and then answered, the saved message held two items with the same id, and opening that chat later locked up the browser tab. Repeated ids are now renamed when the chat is shown, so these chats open normally, including ones saved before this fix. Providers that already send unique ids render exactly as before.
Fixes#31837
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Open WebUI puts the MCP server ID in front of every MCP tool name it offers to the model. When the two together are longer than 64 characters, providers that cap tool names at 64 (the OpenAI API, AWS Bedrock) reject the whole chat request, even if the model never picks that tool. Names over the limit are now cut to 64 characters ending in a short hash, so the same tool always gets the same name and the MCP server is still called with the original tool name. Names that already fit are unchanged.
Fixes#31821
Every chat that got a reply left a small lock behind in the server process, so a long-running server kept one for every chat it had ever answered and only a restart gave the memory back. The lock is now dropped as soon as nothing is using it, so a finished reply leaves nothing behind per chat, while replies, sub-agent results and timers for the same chat still wait for each other as before.
Fixes#31521
Opening a shared chat link while signed out landed on the home page with a blank screen. Only a manual refresh reached the login page, and after signing in the visitor ended up on the home page, so the link had to be opened again. This happened with every sign-in method, OAuth included.
When the share could not be loaded, the share page navigated home twice. The second navigation cancelled the login redirect the first one had started, and since the app shell was already on screen, nothing checked the session again.
The share page now navigates once. Signed-out visitors go to the login page with the share as the redirect target, so they land on the shared chat after signing in, OAuth included, since the login page keeps the target across the provider round trip. Signed-in users on a dead or forbidden link still go home, and open shares still render without signing in.
Fixes#31334
Adding files through `POST /api/v1/knowledge/{id}/files/batch/add` accepted a file whose extracted text was already in the knowledge base under another file, and linked both, while the single-file add rejects the same file with "Duplicate content detected". The same text was then embedded twice and retrieval returned the same passages twice.
The batch path now runs each file's content hash through the same check the single-file path uses, now shared by both, and also against the earlier files of the same batch. A duplicate is reported as a failed file in the batch result and is not linked, while the other files of the batch still go through. Batch-added chunks now carry the content hash in their metadata, so later adds through either endpoint detect them.
Chunks written by batch add before this change have no hash, so content added that way earlier is still not detected as a duplicate.
Verified on a running instance: two files with identical text now end up with exactly one linked in every order and combination (one batch call, separate batch calls, batch mixed with single add), and re-adding the same file is still accepted.
Fixes#31333
With ENABLE_CUSTOM_MODEL_FALLBACK on, a workspace model whose base model is gone should be answered by the first default model. That worked for plain API calls, but every chat sent from the web UI failed with "Model not found" for users and "Model '' was not found" for admins, and no model was called.
Web UI chats carry a chat id and a socket session, so the request is split into one task per selected model. Each task was rebuilt with the originally requested model id, which dropped the fallback chosen earlier in the handler. The task for the requested model now keeps the fallback model when one was chosen. The chat still records the workspace model the user picked.
Tested end to end against a mock upstream, as user and admin, in new and existing chats: before, every web UI send with such a model errored; after, the default model answers. Healthy models, workspace models with a valid base and multi-model sends behave as before, and with the fallback disabled the chat still fails with "Model not found".
Fixes#31345
A user added to an existing group or DM channel saw nothing from it until they reloaded the page: the channel did not appear in their sidebar, and opening it by URL showed the history but no new messages, edits, pins or reactions.
Adding members now does what channel creation already does for its participants: the newly inserted members get a `channel:created` event so their sidebar refreshes, and their open sessions join the channel room so live updates reach them. Standard channels are skipped because their access comes from access grants, matching the membership-removal path.
Verified against a running server with two live Socket.IO clients: the added user's open session now gets the sidebar refresh and the next message immediately; re-adding an existing member, removal and standard channels behave as before.
Fixes#30432
External knowledge bases on the pgvector provider failed on every search with "operator does not exist: vector <=> double precision[]", so they looked empty to users. This happened regardless of the VECTOR_DB setting.
The query embedding was bound as a plain Python list. register_vector only adapts pgvector's own Vector type and numpy arrays, so psycopg sent the list as a float array, which the <=> operator does not accept. Wrapping the embedding in pgvector.Vector sends it as a real vector.
Vector is imported from the package root, which works on the pinned pgvector 0.4.2 and on 0.5.x, where the pgvector.psycopg re-export no longer exists.
Verified against a pgvector Postgres: before the fix the reported error reproduces; after it, results come back ranked by cosine distance and filtered to the collection, including schema-qualified tables, halfvec columns and 1536-dimension embeddings.
Fixes#26663
With VECTOR_DB=elasticsearch, changing a file's content in a knowledge base added the new text but never removed the old chunks, so searches and chats kept returning the old text next to the new. The old chunks are now found and removed after the edit, the same as on the default store.
Fixes#31523
When a model called one tool, got its result and then called a second tool with no text in between, the next request merged both calls into an earlier assistant message that the provider had already seen. That changed the conversation's beginning, so the provider's prompt cache stopped matching from there for the rest of the chat. Each tool call and its result are now sent as their own messages, so the start of the conversation stays identical from one request to the next.
Fixes#31588
In a chat inside a folder with knowledge attached, the chat only searches the folder's knowledge, but a sub-agent it started could list and search every knowledge base the user can read. Sub-agents now get the folder's knowledge like the chat that started them. They already receive the folder's system prompt as part of the chat's instructions, so it is not added a second time.
Fixes#31569
* fix: audit log shows passwords that contain a double quote
With AUDIT_LOG_LEVEL set to REQUEST or REQUEST_RESPONSE, a password containing a double quote was only masked up to that quote, so a new password like Q"secret was logged as "********"secret. A request with whitespace before the colon, such as "new_password" : "secret", was not masked at all. Any field whose name ends in "password" is now masked through its closing quote in both cases.
* fix: audit log records passwords sent back in responses
With AUDIT_LOG_LEVEL set to REQUEST_RESPONSE, fields whose name ends in "password" were masked in request bodies, but response bodies were logged unmasked. Saving or opening the LDAP server settings therefore wrote the Application DN Password to the audit log in plain text, because the settings come back in the response, and the Jupyter passwords in the code execution settings leaked the same way. Responses now get the same masking as requests.
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Native hybrid search on Milvus kept a second, text-only collection beside every Milvus collection and searched both. Each Milvus collection now holds its vectors, its text and its BM25 keyword index together, and results rank exactly as before, with the BM25 weight setting working the same way it does on pgvector. Existing data moves on the first start with ENABLE_DB_MIGRATIONS on: startup waits while every collection is copied once (vectors included, nothing is re-embedded) and the originals are only dropped after every copy succeeded, so a failed run changes nothing and is retried on the next start. The copy needs free disk space for a second copy of the data until it finishes, and on one 16-thread machine with Milvus's official docker compose setup it ran at 11 to 22 MB/s, so 200 GB takes about 2.5 to 5 hours depending on chunk size. Milvus servers older than 2.5 are detected and keep the existing hybrid search.
