mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
webui: add system message in export conversation, support upload conversation with system message Webui: show upload only when in new conversation Webui: Add model name webui: increase height of chat message window when clicking editing Webui: autoclose settings dialog dropdown and maximze screen width when zoom in webui: fix date issues and add more dates webui: change error to toast.error. server: add n_past and slot_id in props_simple webui: add cache tokens, context and prompt speed in chat webui: modernize ui webui: change welcome message webui: change speed display webui: change run python icon webui: add config to use server defaults for sampler webui: put speed on left and context on right webui: recognize AsciiDoc files as valid text files (#16850) * webui: recognize AsciiDoc files as valid text files * webui: add an updated static webui build * webui: add the updated dependency list * webui: re-add an updated static webui build Add a setting to display message generation statistics (#16901) * feat: Add setting to display message generation statistics * chore: build static webui output webui: add HTML/JS preview support to MarkdownContent with sandboxed iframe (#16757) * webui: add HTML/JS preview support to MarkdownContent with sandboxed iframe dialog Extended MarkdownContent to flag previewable code languages, add a preview button alongside copy controls, manage preview dialog state, and share styling for the new button group Introduced CodePreviewDialog.svelte, a sandboxed iframe modal for rendering HTML/JS previews with consistent dialog controls * webui: fullscreen HTML preview dialog using bits-ui * Update tools/server/webui/src/lib/components/app/misc/CodePreviewDialog.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * Update tools/server/webui/src/lib/components/app/misc/MarkdownContent.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * webui: pedantic style tweak for CodePreviewDialog close button * webui: remove overengineered preview language logic * chore: update webui static build --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> webui: auto-refresh /props on inference start to resync model metadata (#16784) * webui: auto-refresh /props on inference start to resync model metadata - Add no-cache headers to /props and /slots - Throttle slot checks to 30s - Prevent concurrent fetches with promise guard - Trigger refresh from chat streaming for legacy and ModelSelector - Show dynamic serverWarning when using cached data * fix: restore proper legacy behavior in webui by using unified /props refresh Updated assistant message bubbles to show each message's stored model when available, falling back to the current server model only when the per-message value is missing When the model selector is disabled, now fetches /props and prioritizes that model name over chunk metadata, then persists it with the streamed message so legacy mode properly reflects the backend configuration * fix: detect first valid SSE chunk and refresh server props once * fix: removed the slots availability throttle constant and state * webui: purge ai-generated cruft * chore: update webui static build feat(webui): improve LaTeX rendering with currency detection (#16508) * webui : Revised LaTeX formula recognition * webui : Further examples containg amounts * webui : vitest for maskInlineLaTeX * webui: Moved preprocessLaTeX to lib/utils * webui: LaTeX in table-cells * chore: update webui build output (use theirs) * webui: backslash in LaTeX-preprocessing * chore: update webui build output * webui: look-behind backslash-check * chore: update webui build output * Apply suggestions from code review Code maintenance (variable names, code formatting, string handling) Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * webui: Moved constants to lib/constants. * webui: package woff2 inside base64 data * webui: LaTeX-line-break in display formula * chore: update webui build output * webui: Bugfix (font embedding) * webui: Bugfix (font embedding) * webui: vite embeds assets * webui: don't suppress 404 (fonts) * refactor: KaTeX integration with SCSS Moves KaTeX styling to SCSS for better customization and font embedding. This change includes: - Adding `sass` as a dev dependency. - Introducing a custom SCSS file to override KaTeX variables and disable TTF/WOFF fonts, relying solely on WOFF2 for embedding. - Adjusting the Vite configuration to resolve `katex-fonts` alias and inject SCSS variables. * fix: LaTeX processing within blockquotes * webui: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> server : add props.model_alias (#16943) * server : add props.model_alias webui: fix keyboard shortcuts for new chat & edit chat title (#17007) Better UX for handling multiple attachments in WebUI (#17246) webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI (#16618) * webui: add OAI-Compat Harmony tool-call live streaming visualization and persistence in chat UI - Purely visual and diagnostic change, no effect on model context, prompt construction, or inference behavior - Captured assistant tool call payloads during streaming and non-streaming completions, and persisted them in chat state and storage for downstream use - Exposed parsed tool call labels beneath the assistant's model info line with graceful fallback when parsing fails - Added tool call badges beneath assistant responses that expose JSON tooltips and copy their payloads when clicked, matching the existing model badge styling - Added a user-facing setting to toggle tool call visibility to the Developer settings section directly under the model selector option * webui: remove scroll listener causing unnecessary layout updates (model selector) * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * chore: npm run format & update webui build output * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> webui: Fix clickability around chat processing statistics UI (#17278) * fix: Better pointer events handling in chat processing info elements * chore: update webui build output Fix merge error webui: Add a "Continue" Action for Assistant Message (#16971) * feat: Add "Continue" action for assistant messages * feat: Continuation logic & prompt improvements * chore: update webui build output * feat: Improve logic for continuing the assistant message * chore: update webui build output * chore: Linting * chore: update webui build output * fix: Remove synthetic prompt logic, use the prefill feature by sending the conversation payload ending with assistant message * chore: update webui build output * feat: Enable "Continue" button based on config & non-reasoning model type * chore: update webui build output * chore: Update packages with `npm audit fix` * fix: Remove redundant error * chore: update webui build output * chore: Update `.gitignore` * fix: Add missing change * feat: Add auto-resizing for Edit Assistant/User Message textareas * chore: update webui build output Improved file naming & structure for UI components (#17405) * refactor: Component iles naming & structure * chore: update webui build output * refactor: Dialog titles + components namig * chore: update webui build output * refactor: Imports * chore: update webui build output webui: hide border of button webui: update webui: update webui: update add vision webui: minor settings reorganization and add disable autoscroll option (#17452) * webui: added a dedicated 'Display' settings section that groups visualization options * webui: added a Display setting to toggle automatic chat scrolling * chore: update webui build output Co-authored-by: firecoperana <firecoperana>
195 lines
5.8 KiB
TypeScript
195 lines
5.8 KiB
TypeScript
// @ts-expect-error this package does not have typing
|
|
import TextLineStream from 'textlinestream';
|
|
import { APIMessage, Message, LlamaCppServerProps, APIMessageContentPart } from './types';
|
|
|
|
// ponyfill for missing ReadableStream asyncIterator on Safari
|
|
import { asyncIterator } from '@sec-ant/readable-stream/ponyfill/asyncIterator';
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
export const isString = (x: any) => !!x.toLowerCase;
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
export const isBoolean = (x: any) => x === true || x === false;
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
export const isNumeric = (n: any) => !isString(n) && !isNaN(n) && !isBoolean(n);
|
|
export const escapeAttr = (str: string) =>
|
|
str.replace(/>/g, '>').replace(/"/g, '"');
|
|
|
|
// wrapper for SSE
|
|
export async function* getSSEStreamAsync(fetchResponse: Response) {
|
|
if (!fetchResponse.body) throw new Error('Response body is empty');
|
|
const lines: ReadableStream<string> = fetchResponse.body
|
|
.pipeThrough(new TextDecoderStream())
|
|
.pipeThrough(new TextLineStream());
|
|
// @ts-expect-error asyncIterator complains about type, but it should work
|
|
for await (const line of asyncIterator(lines)) {
|
|
//if (isDev) console.log({ line });
|
|
if (line.startsWith('data:') && !line.endsWith('[DONE]')) {
|
|
const data = JSON.parse(line.slice(5));
|
|
yield data;
|
|
} else if (line.startsWith('error:')) {
|
|
const data = JSON.parse(line.slice(6));
|
|
throw new Error(data.message || 'Unknown error');
|
|
}
|
|
}
|
|
}
|
|
|
|
// copy text to clipboard
|
|
export const copyStr = (textToCopy: string) => {
|
|
// Navigator clipboard api needs a secure context (https)
|
|
if (navigator.clipboard && window.isSecureContext) {
|
|
navigator.clipboard.writeText(textToCopy);
|
|
} else {
|
|
// Use the 'out of viewport hidden text area' trick
|
|
const textArea = document.createElement('textarea');
|
|
textArea.value = textToCopy;
|
|
// Move textarea out of the viewport so it's not visible
|
|
textArea.style.position = 'absolute';
|
|
textArea.style.left = '-999999px';
|
|
document.body.prepend(textArea);
|
|
textArea.select();
|
|
document.execCommand('copy');
|
|
}
|
|
};
|
|
|
|
/**
|
|
* filter out redundant fields upon sending to API
|
|
* also format extra into text
|
|
*/
|
|
export function normalizeMsgsForAPI(messages: Readonly<Message[]>) {
|
|
return messages.map((msg) => {
|
|
if (msg.role !== 'user' || !msg.extra) {
|
|
return {
|
|
role: msg.role,
|
|
content: msg.content,
|
|
} as APIMessage;
|
|
}
|
|
|
|
// extra content first, then user text message in the end
|
|
// this allow re-using the same cache prefix for long context
|
|
const contentArr: APIMessageContentPart[] = [];
|
|
|
|
for (const extra of msg.extra ?? []) {
|
|
if (extra.type === 'context') {
|
|
contentArr.push({
|
|
type: 'text',
|
|
text: extra.content,
|
|
});
|
|
} else if (extra.type === 'textFile') {
|
|
contentArr.push({
|
|
type: 'text',
|
|
text: `File: ${extra.name}\nContent:\n\n${extra.content}`,
|
|
});
|
|
} else if (extra.type === 'imageFile') {
|
|
contentArr.push({
|
|
type: 'image_url',
|
|
image_url: { url: extra.base64Url },
|
|
});
|
|
} else if (extra.type === 'audioFile') {
|
|
contentArr.push({
|
|
type: 'input_audio',
|
|
input_audio: {
|
|
data: extra.base64Data,
|
|
format: /wav/.test(extra.mimeType) ? 'wav' : 'mp3',
|
|
},
|
|
});
|
|
} else {
|
|
throw new Error('Unknown extra type');
|
|
}
|
|
}
|
|
|
|
// add user message to the end
|
|
contentArr.push({
|
|
type: 'text',
|
|
text: msg.content,
|
|
});
|
|
|
|
return {
|
|
role: msg.role,
|
|
content: contentArr,
|
|
};
|
|
}) as APIMessage[];
|
|
}
|
|
|
|
/**
|
|
* recommended for DeepsSeek-R1, filter out content between <think> and </think> tags
|
|
*/
|
|
export function filterThoughtFromMsgs(messages: APIMessage[]) {
|
|
console.debug({ messages });
|
|
return messages.map((msg) => {
|
|
if (msg.role !== 'assistant') {
|
|
return msg;
|
|
}
|
|
// assistant message is always a string
|
|
const contentStr = msg.content as string;
|
|
return {
|
|
role: msg.role,
|
|
content:
|
|
msg.role === 'assistant'
|
|
? contentStr
|
|
.split(/<\/think>|<\|end\|>/)
|
|
.at(-1)!
|
|
.trim()
|
|
: contentStr,
|
|
} as APIMessage;
|
|
});
|
|
}
|
|
|
|
export function classNames(classes: Record<string, boolean>): string {
|
|
return Object.entries(classes)
|
|
.filter(([_, value]) => value)
|
|
.map(([key, _]) => key)
|
|
.join(' ');
|
|
}
|
|
|
|
export const delay = (ms: number) =>
|
|
new Promise((resolve) => setTimeout(resolve, ms));
|
|
|
|
export const throttle = <T extends unknown[]>(
|
|
callback: (...args: T) => void,
|
|
delay: number
|
|
) => {
|
|
let isWaiting = false;
|
|
|
|
return (...args: T) => {
|
|
if (isWaiting) {
|
|
return;
|
|
}
|
|
|
|
callback(...args);
|
|
isWaiting = true;
|
|
|
|
setTimeout(() => {
|
|
isWaiting = false;
|
|
}, delay);
|
|
};
|
|
};
|
|
|
|
export const cleanCurrentUrl = (removeQueryParams: string[]) => {
|
|
const url = new URL(window.location.href);
|
|
removeQueryParams.forEach((param) => {
|
|
url.searchParams.delete(param);
|
|
});
|
|
window.history.replaceState({}, '', url.toString());
|
|
};
|
|
|
|
export const getServerProps = async (
|
|
baseUrl: string,
|
|
apiKey?: string
|
|
): Promise<LlamaCppServerProps> => {
|
|
try {
|
|
const response = await fetch(`${baseUrl}/v1/props`, {
|
|
headers: {
|
|
'Content-Type': 'application/json',
|
|
...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
|
|
},
|
|
});
|
|
if (!response.ok) {
|
|
//throw new Error('Failed to fetch server props');
|
|
}
|
|
const data = await response.json();
|
|
return data as LlamaCppServerProps;
|
|
} catch (error) {
|
|
//console.error('Error fetching server props:', error);
|
|
//toast.error('Error fetching server props:' +error);
|
|
throw error;
|
|
}
|
|
}; |