server: (webui) add --webui-config (#18028)
* server/webui: add server-side WebUI config support Add CLI arguments --webui-config (inline JSON) and --webui-config-file (file path) to configure WebUI default settings from server side. Backend changes: - Parse JSON once in server_context::load_model() for performance - Cache parsed config in webui_settings member (zero overhead on /props) - Add proper error handling in router mode with try/catch - Expose webui_settings in /props endpoint for both router and child modes Frontend changes: - Add 14 configurable WebUI settings via parameter sync - Add tests for webui settings extraction - Fix subpath support with base path in API calls Addresses feedback from @ngxson and @ggerganov * server: address review feedback from ngxson * server: regenerate README with llama-gen-docs
This commit is contained in:
@@ -1,4 +1,5 @@
|
||||
<script lang="ts">
|
||||
import { base } from '$app/paths';
|
||||
import { AlertTriangle, RefreshCw, Key, CheckCircle, XCircle } from '@lucide/svelte';
|
||||
import { goto } from '$app/navigation';
|
||||
import { Button } from '$lib/components/ui/button';
|
||||
@@ -64,7 +65,7 @@
|
||||
settingsStore.updateConfig('apiKey', apiKeyInput.trim());
|
||||
|
||||
// Test the API key by making a real request to the server
|
||||
const response = await fetch('./props', {
|
||||
const response = await fetch(`${base}/props`, {
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${apiKeyInput.trim()}`
|
||||
|
||||
@@ -130,5 +130,19 @@ describe('ParameterSyncService', () => {
|
||||
expect(result.max_tokens).toBe(-1);
|
||||
expect(result.temperature).toBe(0.7);
|
||||
});
|
||||
|
||||
it('should merge webui settings from props when provided', () => {
|
||||
const result = ParameterSyncService.extractServerDefaults(null, {
|
||||
pasteLongTextToFileLen: 0,
|
||||
pdfAsImage: true,
|
||||
renderUserContentAsMarkdown: false,
|
||||
theme: 'dark'
|
||||
});
|
||||
|
||||
expect(result.pasteLongTextToFileLen).toBe(0);
|
||||
expect(result.pdfAsImage).toBe(true);
|
||||
expect(result.renderUserContentAsMarkdown).toBe(false);
|
||||
expect(result.theme).toBeUndefined();
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -55,7 +55,55 @@ export const SYNCABLE_PARAMETERS: SyncableParameter[] = [
|
||||
{ key: 'dry_allowed_length', serverKey: 'dry_allowed_length', type: 'number', canSync: true },
|
||||
{ key: 'dry_penalty_last_n', serverKey: 'dry_penalty_last_n', type: 'number', canSync: true },
|
||||
{ key: 'max_tokens', serverKey: 'max_tokens', type: 'number', canSync: true },
|
||||
{ key: 'samplers', serverKey: 'samplers', type: 'string', canSync: true }
|
||||
{ key: 'samplers', serverKey: 'samplers', type: 'string', canSync: true },
|
||||
{
|
||||
key: 'pasteLongTextToFileLen',
|
||||
serverKey: 'pasteLongTextToFileLen',
|
||||
type: 'number',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'pdfAsImage', serverKey: 'pdfAsImage', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'showThoughtInProgress',
|
||||
serverKey: 'showThoughtInProgress',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'showToolCalls', serverKey: 'showToolCalls', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'disableReasoningFormat',
|
||||
serverKey: 'disableReasoningFormat',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'keepStatsVisible', serverKey: 'keepStatsVisible', type: 'boolean', canSync: true },
|
||||
{ key: 'showMessageStats', serverKey: 'showMessageStats', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'askForTitleConfirmation',
|
||||
serverKey: 'askForTitleConfirmation',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'disableAutoScroll', serverKey: 'disableAutoScroll', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'renderUserContentAsMarkdown',
|
||||
serverKey: 'renderUserContentAsMarkdown',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'autoMicOnEmpty', serverKey: 'autoMicOnEmpty', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'pyInterpreterEnabled',
|
||||
serverKey: 'pyInterpreterEnabled',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{
|
||||
key: 'enableContinueGeneration',
|
||||
serverKey: 'enableContinueGeneration',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
}
|
||||
];
|
||||
|
||||
export class ParameterSyncService {
|
||||
@@ -74,25 +122,39 @@ export class ParameterSyncService {
|
||||
* Extract server default parameters that can be synced
|
||||
*/
|
||||
static extractServerDefaults(
|
||||
serverParams: ApiLlamaCppServerProps['default_generation_settings']['params'] | null
|
||||
serverParams: ApiLlamaCppServerProps['default_generation_settings']['params'] | null,
|
||||
webuiSettings?: Record<string, string | number | boolean>
|
||||
): ParameterRecord {
|
||||
if (!serverParams) return {};
|
||||
|
||||
const extracted: ParameterRecord = {};
|
||||
|
||||
for (const param of SYNCABLE_PARAMETERS) {
|
||||
if (param.canSync && param.serverKey in serverParams) {
|
||||
const value = (serverParams as unknown as Record<string, ParameterValue>)[param.serverKey];
|
||||
if (value !== undefined) {
|
||||
// Apply precision rounding to avoid JavaScript floating-point issues
|
||||
extracted[param.key] = this.roundFloatingPoint(value);
|
||||
if (serverParams) {
|
||||
for (const param of SYNCABLE_PARAMETERS) {
|
||||
if (param.canSync && param.serverKey in serverParams) {
|
||||
const value = (serverParams as unknown as Record<string, ParameterValue>)[
|
||||
param.serverKey
|
||||
];
|
||||
if (value !== undefined) {
|
||||
// Apply precision rounding to avoid JavaScript floating-point issues
|
||||
extracted[param.key] = this.roundFloatingPoint(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Handle samplers array conversion to string
|
||||
if (serverParams.samplers && Array.isArray(serverParams.samplers)) {
|
||||
extracted.samplers = serverParams.samplers.join(';');
|
||||
}
|
||||
}
|
||||
|
||||
// Handle samplers array conversion to string
|
||||
if (serverParams.samplers && Array.isArray(serverParams.samplers)) {
|
||||
extracted.samplers = serverParams.samplers.join(';');
|
||||
if (webuiSettings) {
|
||||
for (const param of SYNCABLE_PARAMETERS) {
|
||||
if (param.canSync && param.serverKey in webuiSettings) {
|
||||
const value = webuiSettings[param.serverKey];
|
||||
if (value !== undefined) {
|
||||
extracted[param.key] = this.roundFloatingPoint(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return extracted;
|
||||
|
||||
@@ -40,6 +40,10 @@ class ServerStore {
|
||||
return this.props?.default_generation_settings?.n_ctx ?? null;
|
||||
}
|
||||
|
||||
get webuiSettings(): Record<string, string | number | boolean> | undefined {
|
||||
return this.props?.webui_settings;
|
||||
}
|
||||
|
||||
get isRouterMode(): boolean {
|
||||
return this.role === ServerRole.ROUTER;
|
||||
}
|
||||
|
||||
@@ -66,7 +66,8 @@ class SettingsStore {
|
||||
*/
|
||||
private getServerDefaults(): Record<string, string | number | boolean> {
|
||||
const serverParams = serverStore.defaultParams;
|
||||
return serverParams ? ParameterSyncService.extractServerDefaults(serverParams) : {};
|
||||
const webuiSettings = serverStore.webuiSettings;
|
||||
return ParameterSyncService.extractServerDefaults(serverParams, webuiSettings);
|
||||
}
|
||||
|
||||
constructor() {
|
||||
|
||||
+1
@@ -176,6 +176,7 @@ export interface ApiLlamaCppServerProps {
|
||||
bos_token: string;
|
||||
eos_token: string;
|
||||
build_info: string;
|
||||
webui_settings?: Record<string, string | number | boolean>;
|
||||
}
|
||||
|
||||
export interface ApiChatCompletionRequest {
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { base } from '$app/paths';
|
||||
import { error } from '@sveltejs/kit';
|
||||
import { browser } from '$app/environment';
|
||||
import { config } from '$lib/stores/settings.svelte';
|
||||
@@ -22,7 +23,7 @@ export async function validateApiKey(fetch: typeof globalThis.fetch): Promise<vo
|
||||
headers.Authorization = `Bearer ${apiKey}`;
|
||||
}
|
||||
|
||||
const response = await fetch(`./props`, { headers });
|
||||
const response = await fetch(`${base}/props`, { headers });
|
||||
|
||||
if (!response.ok) {
|
||||
if (response.status === 401 || response.status === 403) {
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
<script lang="ts">
|
||||
import '../app.css';
|
||||
import { base } from '$app/paths';
|
||||
import { page } from '$app/state';
|
||||
import { untrack } from 'svelte';
|
||||
import { ChatSidebar, DialogConversationTitleUpdate } from '$lib/components/app';
|
||||
@@ -157,7 +158,7 @@
|
||||
headers.Authorization = `Bearer ${apiKey.trim()}`;
|
||||
}
|
||||
|
||||
fetch(`./props`, { headers })
|
||||
fetch(`${base}/props`, { headers })
|
||||
.then((response) => {
|
||||
if (response.status === 401 || response.status === 403) {
|
||||
window.location.reload();
|
||||
|
||||
Reference in New Issue
Block a user