mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 17:18:49 -04:00
mudler-agentandEttore Di Giacinto
c6687ce67c
* refactor(addons): one name and one verb pair in the add-ons UI The sidebar, the page and the tabs now say Add-ons. The tabs are My add-ons, Find add-ons and Sources. Turn on and Turn off replace Enable, Start, Disable and Stop wherever they label a button, and the state words read On and Off. The subtitle no longer names the owner. Other locales get the new keys; the main labels are translated and the rest carry the English text until a translator refines them. A unit test checks that every locale has the keys of English. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): show what an add-on does on its card and move actions to a menu A card now shows the add-on description, an "Adds a page" line and the number of chat tools when they apply. The pin button and the bare arrows are replaced by one overflow menu with Show in sidebar, Details and Remove. Reordering a pinned add-on stays in the same menu. Remove asks first and runs the typed uninstall action; only administrators see it. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): add a preview pane for the selected add-on Selecting a card, or choosing Details in its menu, opens a pane beside the list. It shows the name and state, the description, what the add-on adds, Turn on or Turn off and Remove, and its version and source. The pane replaces the modal sheet and uses the data the list already has. The source comes from the installed list that the host already serves to administrators. Screenshot slots show only when the host lists images for the add-on; today it lists none, so no slot is drawn. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): clear first-run and empty states for My add-ons With nothing installed, an administrator now sees three add-ons from the sources, each with Install and turn on, and a link to Find add-ons. A search that finds nothing says that no add-on matches and offers to clear the search, instead of saying that nothing is installed. Install and turn on is one action of the user: it installs, then turns the add-on on, with a separate operation identity for each step and the progress or the reason for a failure shown on the card. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): one button and folded details on Find add-ons entries Each entry shows its description, an "Adds a page" label when the library entry declares a main page, and one button: Install and turn on. An add-on that is installed but off offers Turn on. Details is folded into the entry and shows the trust and build facts the entry already carries, so the separate details sheet is gone. A backend keeps a plain Install, because a backend has no on or off. The library entry carries no tool count, so the entry cannot say how many chat tools an add-on adds. That label appears on My add-ons, where the list knows it. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): install and turn on in one dialog with inline progress Install and turn on now asks once. The dialog then stays open and shows two steps, the install and the turn on, and ends on the result or on the reason a step failed with a way to try again. A failed turn on keeps the install and the retry only turns the add-on on. Each step is its own action with its own operation identity, so an unknown outcome still blocks further actions on the add-on until it is read or dismissed. The first-run cards use the same dialog. The two-step flow is a plain function with unit tests. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(addons): fold the Installed tab into My add-ons The page now has three tabs: My add-ons, Find add-ons and Sources. What the Installed tab showed is in the preview pane of each add-on, under More details for administrators: health, trust, compatibility, storage, data recovery and updates, with Check for updates and Upgrade. Remove and Turn on or Turn off are on the card and in the pane. An old ?tab=installed address opens My add-ons, and the management link ?manage=ID opens the details of that add-on. A card shows an update mark when the host reports one. Closing the pane returns focus to its card. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(addons): describe the new add-ons page labels Update the add-ons feature page and the pages that point at it: the sidebar item and the page are called Add-ons, the tabs are My add-ons, Find add-ons and Sources, Turn on and Turn off replace Start and Stop, the card menu replaces the pin control, and the preview pane holds what the Installed tab showed. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(addons): say what is wrong on the page of an add-on that cannot open The page of an add-on that cannot open now depends on the add-on. One that is installed but off says "<name> is off" and offers Turn on to an administrator. One that is not installed says so and sends an administrator to Find add-ons. One that failed shows the reason and a link to its details. A reader gets a line that says who can fix it, and no button. The page title is the name of the add-on, with a capital first letter when the host lists no title, and no longer the bare identifier. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(chat): put the add-on tools control next to MCP and say what off means The add-on tools control moves from the chat header to the composer, right after the MCP control, because both decide what the model may call in this chat. Its menu starts with one line: an add-on that is off here does nothing in this chat. Only add-ons that ship tools appear in it, as before. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(addons): clear lint warnings of the new components Add the lint header the add-on components use for JSX-only imports, drop an unneeded directive, stop exporting a helper from a component file and extract the dependencies of an effect. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(addons): update the backend library specs for the folded entry details A backend says its kind on the entry, an add-on says it under Details, Details is a fold of the entry and an installed backend has no Install button. Assisted-by: Claude:claude-sonnet-5-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
79 lines
7.0 KiB
Markdown
79 lines
7.0 KiB
Markdown
+++
|
|
disableToc = false
|
|
title = "Studio"
|
|
weight = 49
|
|
url = "/features/studio/"
|
|
+++
|
|
|
|
{{% notice note %}}
|
|
Studio is an add-on. It is not part of the web bundle: install it from **Find add-ons** in the [Add-ons](../addons/#the-studio-add-on) page with **Install and turn on**. Once it is usable, it is in My add-ons and can be shown in the sidebar, and it opens at `/app/addons/studio/studio`. The old links (`/app/studio`, `/app/image` and the other generator links) open it there.
|
|
{{% /notice %}}
|
|
|
|
Studio is the part of the web UI where you make images, video, 3D objects, speech, sound and transformed audio, and find what you made before. It opens on a front page with a prompt box and your own work. Each type still has its own workspace page (Images, Video, 3D, TTS, Sound, Transform, Diarization) where a run happens.
|
|
|
|
## Make something
|
|
|
|
Type what you want in the box under **What do you want to make?**, or pick a type first. The box suggests a type from your words ("Sounds like Video") and never switches by itself. The suggestion is a short list of keywords in the browser. No model is called.
|
|
|
|
| Key | Action |
|
|
|---|---|
|
|
| `/` | Focus the prompt box |
|
|
| `Alt+1` to `Alt+7` | Pick a type, in the order of the chips |
|
|
| `Ctrl+Enter` (`Cmd+Enter`) | Generate |
|
|
| `Alt+Enter` | Take the suggested type |
|
|
| `Esc` | Close the details in a lineage view |
|
|
|
|
**Generate** opens the workspace for the chosen type with the prompt, the model, and the options that workspace has already filled in: size and count for Images, size for Video. The run itself happens on the workspace page, as before. The front page does not run anything.
|
|
|
|
3D, Transform and Diarization start from a file. Use the **Start from** list to pick one of your earlier results as the file, or add a file on the next page.
|
|
|
|
### A type with no model
|
|
|
|
A type with no installed model is a dashed chip. Picking it shows one model from the gallery, its download size and memory need where the gallery knows them, the memory free now, and an **Install** button. Nothing installs until you press it, and the words you typed stay in the box while it installs. When the gallery gives no size, the note says so.
|
|
|
|
## Your work
|
|
|
|
**Your work** lists the results this browser has a record of, newest first, with filters for each type and counts. Each tile shows a thumbnail (a waveform drawing for audio, one bar per speaker for diarization), the prompt, the model and the age. The star marks a favourite.
|
|
|
|
Results made from each other stack into one project tile. Open a tile to see the lineage.
|
|
|
|
### Where the history is kept
|
|
|
|
The history lives in your browser, not on the server. Each workspace writes its own list when a result is produced: images, video, TTS, sound and audio transform in browser storage (up to 100 entries each), 3D in IndexedDB (up to 20 entries, with the model file), and diarization in browser storage with the file name, the model and the speaker count only. It never keeps the recording or the transcript. A prompt longer than 2000 characters is cut when it is stored. Favourites are a list of up to 500 ids.
|
|
|
|
Results made before this version have no link to the result they came from, so they appear as single tiles. The files themselves are on the server; if the server has cleaned its output folder, the tile shows the type icon instead of a picture.
|
|
|
|
**Clear history** removes all of these lists and the favourites from this browser after a confirmation. It does not delete files on the server.
|
|
|
|
## Lineage
|
|
|
|
When a workspace is opened from a result (for example **Animate** on a picture), the new result records the id of the result it came from and how: take, animate, to 3D, variation, transform or who spoke. The lineage view draws those links as a board: prompts or files on the left, results next to them, the path through the selected result drawn heavier, and one dashed suggested next step chosen from the installed models.
|
|
|
|
The dock under the board acts on the selected result:
|
|
|
|
- **Run as a new take** opens the same workspace with the prompt, model and size filled in. It is disabled when the original input was not kept (3D, diarization).
|
|
- **Branch from here** opens a draft: choose the next step, edit the words, and **Open in** the workspace with the result as its starting point.
|
|
|
|
A step is listed but disabled, with the reason, when the destination page cannot start from that kind of result yet. Today a video cannot start a sound and a 3D object cannot start a clip.
|
|
|
|
Arrow keys walk the board, `B` branches and `Esc` closes the draft, then the details, then the view.
|
|
|
|
## The workspace page
|
|
|
|
All seven workspaces share one layout, under a row of tabs, one per type:
|
|
|
|
- **Compose card.** Optional sources as dashed chips (a start image, reference images, an end image, avatar audio), or a drop area where the run cannot start without a file (a recording for Diarization, audio for Transform, a picture for 3D). Then the prompt, with starters while it is empty, a model chip, the essential options as chips (size and count, duration and frame rate, voice, mode), and an **Advanced** fold that names what is inside when it is closed. Below that: the memory the model needs and whether it fits, when the gallery knows it, and one button. When the button cannot run, the reason is next to it. With no model for the type, the install note from the front page shows in the card.
|
|
- **Run area.** While a request is out, a job card shows the model and options and the time that has passed. The server reports no phase and no percentage on these endpoints, so the bar is indeterminate. A failed run shows what the server said, says the prompt and settings are still there, and offers **Try again**. A finished run shows the result in a viewer for its type (picture grid, video player, waveform player, 3D viewer, spectrograms, or a timeline of speakers) with a toolbar:
|
|
- **Favourite**, the same list the front page keeps.
|
|
- **Download**.
|
|
- **Use in** lists where the result can go next. A step is disabled, with the reason, when the destination cannot start from it, or when no model for it is installed it says so.
|
|
- **Re-run with edits** puts the result's values back in the form. The fields you then change are outlined and listed under **Changed from this take**, and the button reads **Run again**. It is disabled when the original input was not kept (3D, diarization).
|
|
- **Lineage** opens the lineage view of the front page for this result.
|
|
- **Recent results.** A strip of the results of this type from the same history, with an All and a Favourites filter. Click a tile to show it above, and click it again to go back to the latest.
|
|
|
|
Diarization lists who spoke when as one lane per speaker, the talk time of each speaker, and the segments with their text when the model returned it. **RTTM**, **SRT** (only when there is text) and **JSON** are built in the browser from the result in hand.
|
|
|
|
## What a workspace accepts from the front page
|
|
|
|
The workspaces read these query parameters, so a link of your own works too: `prompt`, `model`, `size`, `n` (count), `from` (the id of the result it starts from) and `edge` (how). For example `/app/studio/video?prompt=Slow%20push-in&from=<id>&edge=animate`.
|