Merge branch 'dev' into fix2345

README.md

@@ -76,31 +76,31 @@ Jan is an open-source ChatGPT alternative that runs 100% offline on your compute
   <tr style="text-align:center">
     <td style="text-align:center"><b>Experimental (Nightly Build)</b></td>
     <td style="text-align:center">
-      <a href='https://delta.jan.ai/latest/jan-win-x64-0.4.8-321.exe'>
+      <a href='https://delta.jan.ai/latest/jan-win-x64-0.4.8-322.exe'>
         <img src='./docs/static/img/windows.png' style="height:14px; width: 14px" />
         <b>jan.exe</b>
       </a>
     </td>
     <td style="text-align:center">
-      <a href='https://delta.jan.ai/latest/jan-mac-x64-0.4.8-321.dmg'>
+      <a href='https://delta.jan.ai/latest/jan-mac-x64-0.4.8-322.dmg'>
         <img src='./docs/static/img/mac.png' style="height:15px; width: 15px" />
         <b>Intel</b>
       </a>
     </td>
     <td style="text-align:center">
-      <a href='https://delta.jan.ai/latest/jan-mac-arm64-0.4.8-321.dmg'>
+      <a href='https://delta.jan.ai/latest/jan-mac-arm64-0.4.8-322.dmg'>
         <img src='./docs/static/img/mac.png' style="height:15px; width: 15px" />
         <b>M1/M2</b>
       </a>
     </td>
     <td style="text-align:center">
-      <a href='https://delta.jan.ai/latest/jan-linux-amd64-0.4.8-321.deb'>
+      <a href='https://delta.jan.ai/latest/jan-linux-amd64-0.4.8-322.deb'>
         <img src='./docs/static/img/linux.png' style="height:14px; width: 14px" />
         <b>jan.deb</b>
       </a>
     </td>
     <td style="text-align:center">
-      <a href='https://delta.jan.ai/latest/jan-linux-x86_64-0.4.8-321.AppImage'>
+      <a href='https://delta.jan.ai/latest/jan-linux-x86_64-0.4.8-322.AppImage'>
         <img src='./docs/static/img/linux.png' style="height:14px; width: 14px" />
         <b>jan.AppImage</b>
       </a>

extensions/monitoring-extension/src/node/index.ts

@@ -2,17 +2,17 @@ import { GpuSetting, GpuSettingInfo, ResourceInfo } from '@janhq/core'
 import { getJanDataFolderPath, log } from '@janhq/core/node'
 import { mem, cpu } from 'node-os-utils'
 import { exec } from 'child_process'
-import { writeFileSync, existsSync, readFileSync } from 'fs'
+import { writeFileSync, existsSync, readFileSync, mkdirSync } from 'fs'
 import path from 'path'
 
+/**
+ * Path to the settings directory
+ **/
+export const SETTINGS_DIR = path.join(getJanDataFolderPath(), 'settings')
 /**
  * Path to the settings file
  **/
-export const GPU_INFO_FILE = path.join(
+export const GPU_INFO_FILE = path.join(SETTINGS_DIR, 'settings.json')
-  getJanDataFolderPath(),
-  'settings',
-  'settings.json'
-)
 
 /**
  * Default GPU settings
@@ -136,6 +136,11 @@ export const updateNvidiaInfo = async () => {
   try {
     JSON.parse(readFileSync(GPU_INFO_FILE, 'utf-8'))
   } catch (error) {
+    if (!existsSync(SETTINGS_DIR)) {
+      mkdirSync(SETTINGS_DIR, {
+        recursive: true,
+      })
+    }
     writeFileSync(GPU_INFO_FILE, JSON.stringify(DEFAULT_SETTINGS, null, 2))
   }
 

extensions/tensorrt-llm-extension/models.json

@@ -33,10 +33,10 @@
     "description": "LlamaCorn is a refined version of TinyLlama-1.1B, optimized for conversational quality, running on consumer devices through TensorRT-LLM",
     "format": "TensorRT-LLM",
     "settings": {
-      "ctx_len": 2048
+      "ctx_len": 2048,
+      "text_model": false
     },
     "parameters": {
-      "stream": true,
       "max_tokens": 4096
     },
     "metadata": {

extensions/tensorrt-llm-extension/src/index.ts

@@ -19,6 +19,7 @@ import {
   systemInformations,
   LocalOAIEngine,
   fs,
+  MessageRequest,
 } from '@janhq/core'
 import models from '../models.json'
 
@@ -144,4 +145,10 @@ export default class TensorRTLLMExtension extends LocalOAIEngine {
     )
     return Promise.resolve()
   }
+
+  inference(data: MessageRequest): void {
+    // TensorRT LLM Extension supports streaming only
+    if (data.model) data.model.parameters.stream = true
+    super.inference(data)
+  }
 }

web/screens/Chat/ChatInput/index.tsx

@@ -244,16 +244,13 @@ const ChatInput: React.FC = () => {
                   <li
                     className={twMerge(
                       'flex w-full cursor-pointer items-center space-x-2 px-4 py-2 text-muted-foreground hover:bg-secondary',
-                      activeThread?.assistants[0].model.settings.vision_model &&
+                      activeThread?.assistants[0].model.settings.text_model ===
-                        activeThread?.assistants[0].model.settings
+                        false
-                          .text_model === false
                         ? 'cursor-not-allowed opacity-50'
                         : 'cursor-pointer'
                     )}
                     onClick={() => {
                       if (
-                        !activeThread?.assistants[0].model.settings
-                          .vision_model ||
                         activeThread?.assistants[0].model.settings
                           .text_model !== false
                       ) {

web/screens/Settings/CoreExtensions/TensorRtExtensionItem.tsx

@@ -123,6 +123,7 @@ const TensorRtExtensionItem: React.FC<Props> = ({ item }) => {
           {item.description}
         </p>
       </div>
+
       {(!compatibility || compatibility['platform']?.includes(PLATFORM)) &&
       isGpuSupported ? (
         <div className="flex min-w-[150px] flex-row justify-end">
@@ -185,15 +186,14 @@ const InstallStateIndicator: React.FC<InstallStateProps> = ({
   onInstallClick,
   onCancelClick,
 }) => {
-  // TODO: NamH support dark mode for this
   if (installProgress !== -1) {
     const progress = installProgress * 100
     return (
-      <div className="flex h-10 flex-row items-center justify-center space-x-2 rounded-md bg-[#EFF8FF] px-4 text-primary">
+      <div className="flex h-10 flex-row items-center justify-center space-x-2 rounded-lg bg-[#EFF8FF] px-4 text-primary dark:bg-secondary">
         <button onClick={onCancelClick} className="font-semibold text-primary">
           Cancel
         </button>
-        <div className="flex w-[113px] flex-row items-center justify-center space-x-2 rounded-md bg-[#D1E9FF] px-2 py-[2px]">
+        <div className="flex w-[113px] flex-row items-center justify-center space-x-2 rounded-md bg-[#D1E9FF] px-2 py-[2px] dark:bg-black/50">
           <Progress className="h-1 w-[69px]" value={progress} />
           <span className="text-xs font-bold text-primary">
             {progress.toFixed(0)}%