Merge branch 'main' into docs/add-guides

README.md

@@ -70,25 +70,25 @@ 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/0.4.3-118/jan-win-x64-0.4.3-118.exe'>
+      <a href='https://delta.jan.ai/0.4.3-121/jan-win-x64-0.4.3-121.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/0.4.3-118/jan-mac-x64-0.4.3-118.dmg'>
+      <a href='https://delta.jan.ai/0.4.3-121/jan-mac-x64-0.4.3-121.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/0.4.3-118/jan-mac-arm64-0.4.3-118.dmg'>
+      <a href='https://delta.jan.ai/0.4.3-121/jan-mac-arm64-0.4.3-121.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/0.4.3-118/jan-linux-amd64-0.4.3-118.deb'>
+      <a href='https://delta.jan.ai/0.4.3-121/jan-linux-amd64-0.4.3-121.deb'>
         <img src='./docs/static/img/linux.png' style="height:14px; width: 14px" />
         <b>jan.deb</b>
       </a>

USAGE.md

@@ -0,0 +1,60 @@
+## Requirements for running Jan App in GPU mode on Windows and Linux
+- You must have an NVIDIA driver that supports CUDA 11.4 or higher. Refer [here](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver).
+    To check if the NVIDIA driver is installed, open PowerShell or Terminal and enter the following command:
+    ```bash
+    nvidia-smi
+    ```
+    If you see a result similar to the following, you have successfully installed the NVIDIA driver:
+    ```bash
+    +-----------------------------------------------------------------------------+
+    | NVIDIA-SMI 470.57.02    Driver Version: 470.57.02    CUDA Version: 11.4     |
+    |-------------------------------+----------------------+----------------------+
+    | GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
+    | Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
+    |                               |                      |               MIG M. |
+    |===============================+======================+======================|
+    |   0  NVIDIA GeForce ...  Off  | 00000000:01:00.0  On |                  N/A |
+    |  0%   51C    P8    10W / 170W |    364MiB /  7982MiB |      0%      Default |
+    |                               |                      |                  N/A |
+    +-------------------------------+----------------------+----------------------+
+    ```
+
+- You must have CUDA 11.4 or higher.
+    To check if CUDA is installed, open PowerShell or Terminal and enter the following command:
+    ```bash
+    nvcc --version
+    ```
+    If you see a result similar to the following, you have successfully installed CUDA:
+    ```bash
+    nvcc: NVIDIA (R) Cuda compiler driver
+
+    Cuda compilation tools, release 11.4, V11.4.100
+    Build cuda_11.4.r11.4/compiler.30033411_0
+    ```
+
+- Specifically for Linux, you will need to have a CUDA compatible driver, refer [here](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver), and you must add the `.so` libraries of CUDA and the CUDA compatible driver to the `LD_LIBRARY_PATH` environment variable, refer [here](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions).
+
+## How to switch mode CPU/GPU Jan app
+
+By default, Jan app will run in CPU mode. When starting Jan app, the program will automatically check if your computer meets the requirements to run in GPU mode. If it does, we will automatically enable GPU mode and pick the GPU has highest VGRAM for you (feature allowing users to select one or more GPU devices for use - currently in planning). You can check whether you are using CPU mode or GPU mode in the settings/advance section of Jan app. (see image below). ![](/docs/static/img/usage/jan-gpu-enable-setting.png)
+
+If you have GPU mode but it is not enabled by default, the following possibilities may exist, you can follow the next steps to fix the error:
+
+1. You have not installed the NVIDIA driver, refer to the NVIDIA driver that supports CUDA 11.4 [here](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver).
+
+2. You have not installed the CUDA toolkit or your CUDA toolkit is not compatible with the NVIDIA driver, refer to CUDA compatibility [here](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver).
+
+3. You have not installed a CUDA compatible driver, refer [here](https://docs.nvidia.com/deploy/cuda-compatibility/index.html#binary-compatibility__table-toolkit-driver), and you must add the `.so` libraries of CUDA and the CUDA compatible driver to the `LD_LIBRARY_PATH` environment variable, refer [here](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions). For Windows, add the `.dll` libraries of CUDA and the CUDA compatible driver to the `PATH` environment variable. Usually, when installing CUDA on Windows, this environment variable is automatically added, but if you do not see it, you can add it manually by referring [here](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html#environment-setup).
+
+## To check the current GPU-related settings that Jan app has detected, you can go to the Settings/Advanced section as shown in the image below.
+![](/docs/static/img/usage/jan-open-home-directory.png)
+![](/docs/static/img/usage/jan-open-settings-1.png)
+![](/docs/static/img/usage/jan-open-settings-2.png)
+![](/docs/static/img/usage/jan-open-settings-3.png)
+
+When you have an issue with GPU mode, share the `settings.json` with us will help us to solve the problem faster.
+
+## Tested on
+
+- Windows 11 Pro 64-bit, NVIDIA GeForce RTX 4070ti GPU, CUDA 12.2, NVIDIA driver 531.18
+- Ubuntu 22.04 LTS, NVIDIA GeForce RTX 4070ti GPU, CUDA 12.2, NVIDIA driver 545

core/src/api/index.ts

@@ -53,9 +53,10 @@ export enum FileSystemRoute {
   writeFileSync = 'writeFileSync',
 }
 export enum FileManagerRoute {
-  synceFile = 'syncFile',
+  syncFile = 'syncFile',
   getUserSpace = 'getUserSpace',
   getResourcePath = 'getResourcePath',
+  fileStat = 'fileStat',
 }
 
 export type ApiFunction = (...args: any[]) => any

core/src/core.ts

@@ -1,3 +1,5 @@
+import { FileStat } from './types'
+
 /**
  * Execute a extension module function in main process
  *
@@ -74,6 +76,15 @@ const openExternalUrl: (url: string) => Promise<any> = (url) =>
  */
 const getResourcePath: () => Promise<string> = () => global.core.api?.getResourcePath()
 
+/**
+ * Gets the file's stats.
+ *
+ * @param path - The path to the file.
+ * @returns {Promise<FileStat>} - A promise that resolves with the file's stats.
+ */
+const fileStat: (path: string) => Promise<FileStat | undefined> = (path) =>
+  global.core.api?.fileStat(path)
+
 /**
  * Register extension point function type definition
  */
@@ -97,4 +108,5 @@ export {
   joinPath,
   openExternalUrl,
   baseName,
+  fileStat,
 }

core/src/node/api/routes/fileManager.ts

@@ -0,0 +1,12 @@
+import { FileManagerRoute } from '../../../api'
+import { HttpServer } from '../../index'
+
+export const fsRouter = async (app: HttpServer) => {
+  app.post(`/app/${FileManagerRoute.syncFile}`, async (request: any, reply: any) => {})
+
+  app.post(`/app/${FileManagerRoute.getUserSpace}`, async (request: any, reply: any) => {})
+
+  app.post(`/app/${FileManagerRoute.getResourcePath}`, async (request: any, reply: any) => {})
+
+  app.post(`/app/${FileManagerRoute.fileStat}`, async (request: any, reply: any) => {})
+}

core/src/types/file/index.ts

@@ -0,0 +1,4 @@
+export type FileStat = {
+  isDirectory: boolean
+  size: number
+}

core/src/types/index.ts

@@ -4,3 +4,4 @@ export * from './thread'
 export * from './message'
 export * from './inference'
 export * from './monitoring'
+export * from './file'

electron/handlers/fileManager.ts

@@ -4,14 +4,17 @@ import reflect from '@alumna/reflect'
 
 import { FileManagerRoute } from '@janhq/core'
 import { userSpacePath, getResourcePath } from './../utils/path'
+import fs from 'fs'
+import { join } from 'path'
+import { FileStat } from '@janhq/core/.'
 
 /**
  * Handles file system extensions operations.
  */
 export function handleFileMangerIPCs() {
-  // Handles the 'synceFile' IPC event. This event is triggered to synchronize a file from a source path to a destination path.
+  // Handles the 'syncFile' IPC event. This event is triggered to synchronize a file from a source path to a destination path.
   ipcMain.handle(
-    FileManagerRoute.synceFile,
+    FileManagerRoute.syncFile,
     async (_event, src: string, dest: string) => {
       return reflect({
         src,
@@ -31,7 +34,33 @@ export function handleFileMangerIPCs() {
   )
 
   // Handles the 'getResourcePath' IPC event. This event is triggered to get the resource path.
-  ipcMain.handle(FileManagerRoute.getResourcePath, async (_event) => {
-    return getResourcePath()
-  })
+  ipcMain.handle(FileManagerRoute.getResourcePath, async (_event) =>
+    getResourcePath()
+  )
+
+  // handle fs is directory here
+  ipcMain.handle(
+    FileManagerRoute.fileStat,
+    async (_event, path: string): Promise<FileStat | undefined> => {
+      const normalizedPath = path
+        .replace(`file://`, '')
+        .replace(`file:/`, '')
+        .replace(`file:\\\\`, '')
+        .replace(`file:\\`, '')
+
+      const fullPath = join(userSpacePath, normalizedPath)
+      const isExist = fs.existsSync(fullPath)
+      if (!isExist) return undefined
+
+      const isDirectory = fs.lstatSync(fullPath).isDirectory()
+      const size = fs.statSync(fullPath).size
+
+      const fileStat: FileStat = {
+        isDirectory,
+        size,
+      }
+
+      return fileStat
+    }
+  )
 }

extensions/inference-nitro-extension/bin/version.txt

@@ -1 +1 @@
-0.1.32
+0.1.34

extensions/inference-nitro-extension/download.bat

@@ -1,3 +1,3 @@
 @echo off
 set /p NITRO_VERSION=<./bin/version.txt
-.\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%NITRO_VERSION%/nitro-%NITRO_VERSION%-win-amd64-cuda.tar.gz -e --strip 1 -o ./bin/win-cuda && .\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%NITRO_VERSION%/nitro-%NITRO_VERSION%-win-amd64.tar.gz -e --strip 1 -o ./bin/win-cpu
+.\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%NITRO_VERSION%/nitro-%NITRO_VERSION%-win-amd64-cuda-12-0.tar.gz -e --strip 1 -o ./bin/win-cuda-12-0 && .\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%NITRO_VERSION%/nitro-%NITRO_VERSION%-win-amd64-cuda-11-4.tar.gz -e --strip 1 -o ./bin/win-cuda-11-4 && .\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%NITRO_VERSION%/nitro-%NITRO_VERSION%-win-amd64.tar.gz -e --strip 1 -o ./bin/win-cpu

extensions/inference-nitro-extension/package.json

@@ -8,7 +8,7 @@
   "license": "AGPL-3.0",
   "scripts": {
     "build": "tsc -b . && webpack --config webpack.config.js",
-    "downloadnitro:linux": "NITRO_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-cpu && chmod +x ./bin/linux-cpu/nitro && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-linux-amd64-cuda.tar.gz -e --strip 1 -o ./bin/linux-cuda && chmod +x ./bin/linux-cuda/nitro",
+    "downloadnitro:linux": "NITRO_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-cpu && chmod +x ./bin/linux-cpu/nitro && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-linux-amd64-cuda-12-0.tar.gz -e --strip 1 -o ./bin/linux-cuda-12-0 && chmod +x ./bin/linux-cuda-12-0/nitro && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-linux-amd64-cuda-11-4.tar.gz -e --strip 1 -o ./bin/linux-cuda-11-4 && chmod +x ./bin/linux-cuda-11-4/nitro",
     "downloadnitro:darwin": "NITRO_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-mac-arm64.tar.gz -e --strip 1 -o ./bin/mac-arm64 && chmod +x ./bin/mac-arm64/nitro && download https://github.com/janhq/nitro/releases/download/v${NITRO_VERSION}/nitro-${NITRO_VERSION}-mac-amd64.tar.gz -e --strip 1 -o ./bin/mac-x64 && chmod +x ./bin/mac-x64/nitro",
     "downloadnitro:win32": "download.bat",
     "downloadnitro": "run-script-os",

extensions/inference-nitro-extension/src/helpers/sse.ts

@@ -30,7 +30,10 @@ export function requestInference(
       signal: controller?.signal,
     })
       .then(async (response) => {
-        if (model.parameters.stream) {
+        if (model.parameters.stream === false) {
+          const data = await response.json();
+          subscriber.next(data.choices[0]?.message?.content ?? "");
+        } else {
           const stream = response.body;
           const decoder = new TextDecoder("utf-8");
           const reader = stream?.getReader();
@@ -54,9 +57,6 @@ export function requestInference(
               }
             }
           }
-        } else {
-          const data = await response.json();
-          subscriber.next(data.choices[0]?.message?.content ?? "");
         }
         subscriber.complete();
       })

extensions/inference-nitro-extension/src/module.ts

@@ -85,28 +85,40 @@ function checkFileExistenceInPaths(file: string, paths: string[]): boolean {
 }
 
 function updateCudaExistence() {
-  let files: string[];
+  let filesCuda12: string[];
+  let filesCuda11: string[];
   let paths: string[];
+  let cudaVersion: string = "";
 
   if (process.platform === "win32") {
-    files = ["cublas64_12.dll", "cudart64_12.dll", "cublasLt64_12.dll"];
+    filesCuda12 = ["cublas64_12.dll", "cudart64_12.dll", "cublasLt64_12.dll"];
+    filesCuda11 = ["cublas64_11.dll", "cudart64_11.dll", "cublasLt64_11.dll"];
     paths = process.env.PATH ? process.env.PATH.split(path.delimiter) : [];
-    const nitro_cuda_path = path.join(__dirname, "bin", "win-cuda");
-    paths.push(nitro_cuda_path);
   } else {
-    files = ["libcudart.so.12", "libcublas.so.12", "libcublasLt.so.12"];
+    filesCuda12 = ["libcudart.so.12", "libcublas.so.12", "libcublasLt.so.12"];
+    filesCuda11 = ["libcudart.so.11.0", "libcublas.so.11", "libcublasLt.so.11"];
     paths = process.env.LD_LIBRARY_PATH
       ? process.env.LD_LIBRARY_PATH.split(path.delimiter)
       : [];
-    const nitro_cuda_path = path.join(__dirname, "bin", "linux-cuda");
-    paths.push(nitro_cuda_path);
     paths.push("/usr/lib/x86_64-linux-gnu/");
   }
 
-  let cudaExists = files.every(
+  let cudaExists = filesCuda12.every(
     (file) => existsSync(file) || checkFileExistenceInPaths(file, paths)
   );
 
+  if (!cudaExists) {
+    cudaExists = filesCuda11.every(
+      (file) => existsSync(file) || checkFileExistenceInPaths(file, paths)
+    );
+    if (cudaExists) {
+      cudaVersion = "11";
+    }
+  }
+  else {
+    cudaVersion = "12";
+  }
+
   let data;
   try {
     data = JSON.parse(readFileSync(NVIDIA_INFO_FILE, "utf-8"));
@@ -115,6 +127,7 @@ function updateCudaExistence() {
   }
 
   data["cuda"].exist = cudaExists;
+  data["cuda"].version = cudaVersion;
   if (cudaExists) {
     data.run_mode = "gpu";
   }
@@ -376,12 +389,17 @@ function spawnNitroProcess(nitroResourceProbe: any): Promise<any> {
     let cudaVisibleDevices = "";
     let binaryName;
     if (process.platform === "win32") {
-      let nvida_info = JSON.parse(readFileSync(NVIDIA_INFO_FILE, "utf-8"));
-      if (nvida_info["run_mode"] === "cpu") {
+      let nvidiaInfo = JSON.parse(readFileSync(NVIDIA_INFO_FILE, "utf-8"));
+      if (nvidiaInfo["run_mode"] === "cpu") {
         binaryFolder = path.join(binaryFolder, "win-cpu");
       } else {
-        binaryFolder = path.join(binaryFolder, "win-cuda");
-        cudaVisibleDevices = nvida_info["gpu_highest_vram"];
+        if (nvidiaInfo["cuda"].version === "12") {
+          binaryFolder = path.join(binaryFolder, "win-cuda-12-0");
+        }
+        else {
+          binaryFolder = path.join(binaryFolder, "win-cuda-11-4");
+        }
+        cudaVisibleDevices = nvidiaInfo["gpu_highest_vram"];
       }
       binaryName = "nitro.exe";
     } else if (process.platform === "darwin") {
@@ -392,12 +410,17 @@ function spawnNitroProcess(nitroResourceProbe: any): Promise<any> {
       }
       binaryName = "nitro";
     } else {
-      let nvida_info = JSON.parse(readFileSync(NVIDIA_INFO_FILE, "utf-8"));
-      if (nvida_info["run_mode"] === "cpu") {
+      let nvidiaInfo = JSON.parse(readFileSync(NVIDIA_INFO_FILE, "utf-8"));
+      if (nvidiaInfo["run_mode"] === "cpu") {
         binaryFolder = path.join(binaryFolder, "linux-cpu");
       } else {
-        binaryFolder = path.join(binaryFolder, "linux-cuda");
-        cudaVisibleDevices = nvida_info["gpu_highest_vram"];
+        if (nvidiaInfo["cuda"].version === "12") {
+          binaryFolder = path.join(binaryFolder, "linux-cuda-12-0");
+        }
+        else {
+          binaryFolder = path.join(binaryFolder, "linux-cuda-11-4");
+        }
+        cudaVisibleDevices = nvidiaInfo["gpu_highest_vram"];
       }
       binaryName = "nitro";
     }

extensions/inference-openai-extension/src/helpers/sse.ts

@@ -46,7 +46,10 @@ export function requestInference(
           subscriber.complete();
           return;
         }
-        if (model.parameters.stream) {
+        if (model.parameters.stream === false) {
+          const data = await response.json();
+          subscriber.next(data.choices[0]?.message?.content ?? "");
+        } else {
           const stream = response.body;
           const decoder = new TextDecoder("utf-8");
           const reader = stream?.getReader();
@@ -70,9 +73,6 @@ export function requestInference(
               }
             }
           }
-        } else {
-          const data = await response.json();
-          subscriber.next(data.choices[0]?.message?.content ?? "");
         }
         subscriber.complete();
       })