fix: populate engines, models and legacy settings

core/src/browser/extensions/enginesManagement.ts

@@ -55,7 +55,18 @@ export abstract class EngineManagementExtension extends BaseExtension {
    * @param name - Inference engine name.
    * @returns A Promise that resolves to intall of engine.
    */
-  abstract installEngine(name: string, engineConfig: EngineConfig): Promise<{ messages: string }>
+  abstract installEngine(
+    name: string,
+    engineConfig: EngineConfig
+  ): Promise<{ messages: string }>
+
+  /**
+   * Add a new remote engine
+   * @returns A Promise that resolves to intall of engine.
+   */
+  abstract addRemoteEngine(
+    engineConfig: EngineConfig
+  ): Promise<{ messages: string }>
 
   /**
    * @param name - Inference engine name.
@@ -70,7 +81,9 @@ export abstract class EngineManagementExtension extends BaseExtension {
    * @param name - Inference engine name.
    * @returns A Promise that resolves to an object of default engine.
    */
-  abstract getDefaultEngineVariant(name: InferenceEngine): Promise<DefaultEngineVariant>
+  abstract getDefaultEngineVariant(
+    name: InferenceEngine
+  ): Promise<DefaultEngineVariant>
 
   /**
    * @body variant - string

core/src/node/helper/config.ts

@@ -1,8 +1,7 @@
-import { AppConfiguration, SettingComponentProps } from '../../types'
+import { AppConfiguration } from '../../types'
 import { join, resolve } from 'path'
 import fs from 'fs'
 import os from 'os'
-import childProcess from 'child_process'
 const configurationFileName = 'settings.json'
 
 /**
@@ -19,7 +18,9 @@ export const getAppConfigurations = (): AppConfiguration => {
 
   if (!fs.existsSync(configurationFile)) {
     // create default app config if we don't have one
-    console.debug(`App config not found, creating default config at ${configurationFile}`)
+    console.debug(
+      `App config not found, creating default config at ${configurationFile}`
+    )
     fs.writeFileSync(configurationFile, JSON.stringify(appDefaultConfiguration))
     return appDefaultConfiguration
   }
@@ -30,20 +31,28 @@ export const getAppConfigurations = (): AppConfiguration => {
     )
     return appConfigurations
   } catch (err) {
-    console.error(`Failed to read app config, return default config instead! Err: ${err}`)
+    console.error(
+      `Failed to read app config, return default config instead! Err: ${err}`
+    )
     return defaultAppConfig()
   }
 }
 
 const getConfigurationFilePath = () =>
   join(
-    global.core?.appPath() || process.env[process.platform == 'win32' ? 'USERPROFILE' : 'HOME'],
+    global.core?.appPath() ||
+      process.env[process.platform == 'win32' ? 'USERPROFILE' : 'HOME'],
     configurationFileName
   )
 
-export const updateAppConfiguration = (configuration: AppConfiguration): Promise<void> => {
+export const updateAppConfiguration = (
+  configuration: AppConfiguration
+): Promise<void> => {
   const configurationFile = getConfigurationFilePath()
-  console.debug('updateAppConfiguration, configurationFile: ', configurationFile)
+  console.debug(
+    'updateAppConfiguration, configurationFile: ',
+    configurationFile
+  )
 
   fs.writeFileSync(configurationFile, JSON.stringify(configuration))
   return Promise.resolve()
@@ -69,86 +78,6 @@ export const getJanExtensionsPath = (): string => {
   return join(appConfigurations.data_folder, 'extensions')
 }
 
-/**
- * Utility function to physical cpu count
- *
- * @returns {number} The physical cpu count.
- */
-export const physicalCpuCount = async (): Promise<number> => {
-  const platform = os.platform()
-  try {
-    if (platform === 'linux') {
-      const output = await exec('lscpu -p | egrep -v "^#" | sort -u -t, -k 2,4 | wc -l')
-      return parseInt(output.trim(), 10)
-    } else if (platform === 'darwin') {
-      const output = await exec('sysctl -n hw.physicalcpu_max')
-      return parseInt(output.trim(), 10)
-    } else if (platform === 'win32') {
-      const output = await exec('WMIC CPU Get NumberOfCores')
-      return output
-        .split(os.EOL)
-        .map((line: string) => parseInt(line))
-        .filter((value: number) => !isNaN(value))
-        .reduce((sum: number, number: number) => sum + number, 1)
-    } else {
-      const cores = os.cpus().filter((cpu: any, index: number) => {
-        const hasHyperthreading = cpu.model.includes('Intel')
-        const isOdd = index % 2 === 1
-        return !hasHyperthreading || isOdd
-      })
-      return cores.length
-    }
-  } catch (err) {
-    console.warn('Failed to get physical CPU count', err)
-    // Divide by 2 to get rid of hyper threading
-    const coreCount = Math.ceil(os.cpus().length / 2)
-    console.debug('Using node API to get physical CPU count:', coreCount)
-    return coreCount
-  }
-}
-
-const exec = async (command: string): Promise<string> => {
-  return new Promise((resolve, reject) => {
-    childProcess.exec(command, { encoding: 'utf8' }, (error, stdout) => {
-      if (error) {
-        reject(error)
-      } else {
-        resolve(stdout)
-      }
-    })
-  })
-}
-
-// a hacky way to get the api key. we should comes up with a better
-// way to handle this
-export const getEngineConfiguration = async (engineId: string) => {
-  if (engineId !== 'openai' && engineId !== 'groq') return undefined
-
-  const settingDirectoryPath = join(
-    getJanDataFolderPath(),
-    'settings',
-    '@janhq',
-    engineId === 'openai' ? 'inference-openai-extension' : 'inference-groq-extension',
-    'settings.json'
-  )
-
-  const content = fs.readFileSync(settingDirectoryPath, 'utf-8')
-  const settings: SettingComponentProps[] = JSON.parse(content)
-  const apiKeyId = engineId === 'openai' ? 'openai-api-key' : 'groq-api-key'
-  const keySetting = settings.find((setting) => setting.key === apiKeyId)
-  let fullUrl = settings.find((setting) => setting.key === 'chat-completions-endpoint')
-    ?.controllerProps.value
-
-  let apiKey = keySetting?.controllerProps.value
-  if (typeof apiKey !== 'string') apiKey = ''
-  if (typeof fullUrl !== 'string') fullUrl = ''
-
-  return {
-    api_key: apiKey,
-    full_url: fullUrl,
-  }
-}
-
 /**
  * Default app configurations
  * App Data Folder default to Electron's userData
@@ -158,7 +87,10 @@ export const getEngineConfiguration = async (engineId: string) => {
  */
 export const defaultAppConfig = (): AppConfiguration => {
   const { app } = require('electron')
-  const defaultJanDataFolder = join(app?.getPath('userData') ?? os?.homedir() ?? '', 'data')
+  const defaultJanDataFolder = join(
+    app?.getPath('userData') ?? os?.homedir() ?? '',
+    'data'
+  )
   return {
     data_folder:
       process.env.CI === 'e2e'

core/src/node/helper/resource.ts

@@ -1,13 +1,8 @@
 import { SystemResourceInfo } from '../../types'
-import { physicalCpuCount } from './config'
-import { log } from './logger'
 
 export const getSystemResourceInfo = async (): Promise<SystemResourceInfo> => {
-  const cpu = await physicalCpuCount()
-  log(`[CORTEX]::CPU information - ${cpu}`)
-
   return {
-    numCpuPhysicalCore: cpu,
+    numCpuPhysicalCore: 0,
     memAvailable: 0, // TODO: this should not be 0
   }
 }

core/src/types/engine/index.ts

@@ -1,7 +1,7 @@
 import { InferenceEngine } from '../../types'
 
 export type Engines = {
-  [key in InferenceEngine]: EngineVariant[]
+  [key in InferenceEngine]: (EngineVariant & EngineConfig)[]
 }
 
 export type EngineMetadata = {
@@ -40,6 +40,7 @@ export type EngineReleased = {
 }
 
 export type EngineConfig = {
+  engine?: string
   version?: string
   variant?: string
   type?: string

core/src/types/message/messageEntity.ts

@@ -32,9 +32,8 @@ export type ThreadMessage = {
   completed_at: number
   /** The additional metadata of this message. **/
   metadata?: Record<string, unknown>
-
+  /** Type of the message */
   type?: string
-
   /** The error code which explain what error type. Used in conjunction with MessageStatus.Error */
   error_code?: ErrorCode
 }
@@ -72,6 +71,10 @@ export type MessageRequest = {
   // TODO: deprecate threadId field
   thread?: Thread
 
+  /** Engine name to process */
+  engine?: string
+
+  /** Message type */
   type?: string
 }
 
@@ -147,7 +150,9 @@ export interface Attachment {
   /**
    * The tools to add this file to.
    */
-  tools?: Array<CodeInterpreterTool | Attachment.AssistantToolsFileSearchTypeOnly>
+  tools?: Array<
+    CodeInterpreterTool | Attachment.AssistantToolsFileSearchTypeOnly
+  >
 }
 
 export namespace Attachment {
@@ -166,5 +171,10 @@ export interface IncompleteDetails {
   /**
    * The reason the message is incomplete.
    */
-  reason: 'content_filter' | 'max_tokens' | 'run_cancelled' | 'run_expired' | 'run_failed'
+  reason:
+    | 'content_filter'
+    | 'max_tokens'
+    | 'run_cancelled'
+    | 'run_expired'
+    | 'run_failed'
 }

extensions/engine-management-extension/engines.mjs

@@ -0,0 +1,27 @@
+import anthropic from './resources/anthropic.json' with { type: 'json' }
+import openai from './resources/openai.json' with { type: 'json' }
+import openrouter from './resources/openrouter.json' with { type: 'json' }
+import groq from './resources/groq.json' with { type: 'json' }
+import martian from './resources/martian.json' with { type: 'json' }
+import mistral from './resources/mistral.json' with { type: 'json' }
+import nvidia from './resources/nvidia.json' with { type: 'json' }
+
+import openaiModels from './models/openai.json' with { type: 'json' }
+import anthropicModels from './models/anthropic.json' with { type: 'json' }
+import openrouterModels from './models/openrouter.json' with { type: 'json' }
+import groqModels from './models/groq.json' with { type: 'json' }
+import martianModels from './models/martian.json' with { type: 'json' }
+import mistralModels from './models/mistral.json' with { type: 'json' }
+import nvidiaModels from './models/nvidia.json' with { type: 'json' }
+
+const engines = [anthropic, openai, openrouter, groq, mistral, martian, nvidia]
+const models = [
+  ...openaiModels,
+  ...anthropicModels,
+  ...openrouterModels,
+  ...groqModels,
+  ...mistralModels,
+  ...martianModels,
+  ...nvidiaModels,
+]
+export { engines, models }

extensions/inference-anthropic-extension/resources/models.json → extensions/engine-management-extension/models/anthropic.json

@@ -1,74 +1,41 @@
 [
   {
-    "sources": [
-      {
-        "url": "https://www.anthropic.com/"
-      }
-    ],
-    "id": "claude-3-opus-latest",
+    "model": "claude-3-opus-latest",
     "object": "model",
     "name": "Claude 3 Opus Latest",
     "version": "1.0",
     "description": "Claude 3 Opus is a powerful model suitables for highly complex task.",
-    "format": "api",
-    "settings": {},
-    "parameters": {
+    "inference_params": {
       "max_tokens": 4096,
       "temperature": 0.7,
       "stream": false
     },
-    "metadata": {
-      "author": "Anthropic",
-      "tags": ["General", "Big Context Length"]
-    },
     "engine": "anthropic"
   },
   {
-    "sources": [
-      {
-        "url": "https://www.anthropic.com/"
-      }
-    ],
-    "id": "claude-3-5-haiku-latest",
+    "model": "claude-3-5-haiku-latest",
     "object": "model",
     "name": "Claude 3.5 Haiku Latest",
     "version": "1.0",
     "description": "Claude 3.5 Haiku is the fastest model provides near-instant responsiveness.",
-    "format": "api",
-    "settings": {},
-    "parameters": {
+    "inference_params": {
       "max_tokens": 8192,
       "temperature": 0.7,
       "stream": false
     },
-    "metadata": {
-      "author": "Anthropic",
-      "tags": ["General", "Big Context Length"]
-    },
     "engine": "anthropic"
   },
   {
-    "sources": [
-      {
-        "url": "https://www.anthropic.com/"
-      }
-    ],
-    "id": "claude-3-5-sonnet-latest",
+    "model": "claude-3-5-sonnet-latest",
     "object": "model",
     "name": "Claude 3.5 Sonnet Latest",
     "version": "1.0",
     "description": "Claude 3.5 Sonnet raises the industry bar for intelligence, outperforming competitor models and Claude 3 Opus on a wide range of evaluations, with the speed and cost of our mid-tier model, Claude 3 Sonnet.",
-    "format": "api",
-    "settings": {},
-    "parameters": {
+    "inference_params": {
       "max_tokens": 8192,
       "temperature": 0.7,
       "stream": true
     },
-    "metadata": {
-      "author": "Anthropic",
-      "tags": ["General", "Big Context Length"]
-    },
     "engine": "anthropic"
   }
 ]