Merge branch 'dev' into main

.github/ISSUE_TEMPLATE/bug_report.md

@@ -25,16 +25,13 @@ If applicable, add screenshots to help explain your issue.
 
 **Environment details**
 - Operating System: [Specify your OS. e.g., MacOS Sonoma 14.2.1, Windows 11, Ubuntu 22, etc]
-- Jan Version: [e.g., 0.4.3]
+- Jan Version: [e.g., 0.4.xxx nightly or manual]
 - Processor: [e.g., Apple M1, Intel Core i7, AMD Ryzen 5, etc]
 - RAM: [e.g., 8GB, 16GB]
 - Any additional relevant hardware specifics: [e.g., Graphics card, SSD/HDD]
 
 **Logs**
-If the cause of the error is not clear, kindly provide your usage logs:
-- `tail -n 50 ~/jan/logs/app.log` if you are using the UI
-- `tail -n 50 ~/jan/logs/server.log` if you are using the local api server
-Making sure to redact any private information.
+If the cause of the error is not clear, kindly provide your usage logs: https://jan.ai/docs/troubleshooting#how-to-get-error-logs
 
 **Additional context**
 Add any other context or information that could be helpful in diagnosing the problem.

.github/workflows/jan-electron-build-nightly.yml

@@ -1,12 +1,6 @@
-name: Jan Build Electron App Nightly or Manual
+name: Electron Builder - Nightly / Manual
 
 on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - 'README.md'
-      - 'docs/**'
   schedule:
     - cron: '0 20 * * 1,2,3' # At 8 PM UTC on Monday, Tuesday, and Wednesday which is 3 AM UTC+7 Tuesday, Wednesday, and Thursday
   workflow_dispatch:

.github/workflows/jan-electron-build.yml

@@ -1,4 +1,4 @@
-name: Jan Build Electron App
+name: Electron Builder - Tag
 
 on:
   push:

.github/workflows/jan-electron-linter-and-test.yml

@@ -1,4 +1,4 @@
-name: Jan Electron Linter & Test
+name: Test - Linter & Playwright
 on:
   workflow_dispatch:
   push:

.github/workflows/jan-openai-api-test.yml

@@ -0,0 +1,90 @@
+name: Test - OpenAI API Pytest collection
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+      - dev
+      - release/**
+    paths:
+      - "docs/**"
+
+  pull_request:
+    branches:
+      - main
+      - dev
+      - release/**
+    paths:
+      - "docs/**"
+
+jobs:
+  openai-python-tests:
+    runs-on: [self-hosted, Linux, ubuntu-desktop]
+    if: (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository) || github.event_name == 'push' || github.event_name == 'workflow_dispatch'
+    steps:
+      - name: Getting the repo
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Installing node
+        uses: actions/setup-node@v3
+        with:
+          node-version: 20
+
+      - name: "Cleanup cache"
+        continue-on-error: true
+        run: |
+          rm -rf ~/jan
+          make clean
+
+      - name: install dependencies
+        run: |
+          npm install -g @stoplight/prism-cli
+
+      - name: create python virtual environment and run test
+        run: |
+          python3 -m venv /tmp/jan
+          source /tmp/jan/bin/activate
+          # Clone openai-api-python repo
+          OPENAI_API_PYTHON_TAG=$(cat docs/openapi/version.txt)
+          git clone https://github.com/openai/openai-python.git
+          cd openai-python
+          git checkout $OPENAI_API_PYTHON_TAG
+
+          python3 -m venv /tmp/jan
+          source /tmp/jan/bin/activate
+          pip install -r requirements-dev.lock
+          pip install pytest-reportportal pytest-html
+          
+          # Create pytest.ini file with content
+          cat ../docs/tests/pytest.ini >> pytest.ini
+          echo "rp_api_key = ${{ secrets.REPORT_PORTAL_API_KEY }}" >> pytest.ini
+          echo "rp_endpoint = ${{ secrets.REPORT_PORTAL_URL_PYTEST }}" >> pytest.ini
+          cat pytest.ini
+          
+          # Append to conftest.py
+          cat ../docs/tests/conftest.py >> tests/conftest.py
+
+          # start mock server and run test then stop mock server
+          prism mock ../docs/openapi/jan.yaml > prism.log & prism_pid=$! && pytest --reportportal --html=report.html && kill $prism_pid
+          deactivate
+
+      - name: Upload Artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: report
+          path: |
+            openai-python/report.html
+            openai-python/assets
+            openai-python/prism.log
+
+      - name: clean up
+        if: always()
+        run: |
+          rm -rf /tmp/jan
+          rm -rf openai-python
+          rm -rf report.html
+          rm -rf report.zip
+  
+

.github/workflows/jan-server-build-nightly.yml

@@ -1,4 +1,4 @@
-name: Jan Build Docker Nightly or Manual
+name: Docker Builder - Nightly / Manual
 
 on:
   push:

.github/workflows/jan-server-build.yml

@@ -1,4 +1,4 @@
-name: Jan Build Docker
+name: Docker Builder - Tag
 
 on:
   push:

core/src/browser/extensions/engines/OAIEngine.ts

@@ -31,6 +31,12 @@ export abstract class OAIEngine extends AIEngine {
   // The loaded model instance
   loadedModel: Model | undefined
 
+  // Transform the payload
+  transformPayload?: Function
+
+  // Transform the response
+  transformResponse?: Function
+
   /**
    * On extension load, subscribe to events.
    */
@@ -78,13 +84,23 @@ export abstract class OAIEngine extends AIEngine {
     }
 
     const header = await this.headers()
+    let requestBody = {
+      messages: data.messages ?? [],
+      model: model.id,
+      stream: true,
+      ...model.parameters,
+    }
+    if (this.transformPayload) {
+      requestBody = this.transformPayload(requestBody)
+    }
 
     requestInference(
       this.inferenceUrl,
-      data.messages ?? [],
+      requestBody,
       model,
       this.controller,
-      header
+      header,
+      this.transformResponse
     ).subscribe({
       next: (content: any) => {
         const messageContent: ThreadContent = {

core/src/browser/extensions/engines/helpers/sse.ts

@@ -7,21 +7,16 @@ import { ErrorCode, ModelRuntimeParams } from '../../../../types'
  */
 export function requestInference(
   inferenceUrl: string,
-  recentMessages: any[],
+  requestBody: any,
   model: {
     id: string
     parameters: ModelRuntimeParams
   },
   controller?: AbortController,
-  headers?: HeadersInit
+  headers?: HeadersInit,
+  transformResponse?: Function
 ): Observable<string> {
   return new Observable((subscriber) => {
-    const requestBody = JSON.stringify({
-      messages: recentMessages,
-      model: model.id,
-      stream: true,
-      ...model.parameters,
-    })
     fetch(inferenceUrl, {
       method: 'POST',
       headers: {
@@ -30,17 +25,17 @@ export function requestInference(
         'Accept': model.parameters.stream ? 'text/event-stream' : 'application/json',
         ...headers,
       },
-      body: requestBody,
+      body: JSON.stringify(requestBody),
       signal: controller?.signal,
     })
       .then(async (response) => {
         if (!response.ok) {
           const data = await response.json()
-          let errorCode = ErrorCode.Unknown;
+          let errorCode = ErrorCode.Unknown
           if (data.error) {
             errorCode = data.error.code ?? data.error.type ?? ErrorCode.Unknown
           } else if (response.status === 401) {
-            errorCode = ErrorCode.InvalidApiKey;
+            errorCode = ErrorCode.InvalidApiKey
           }
           const error = {
             message: data.error?.message ?? 'Error occurred.',
@@ -52,7 +47,11 @@ export function requestInference(
         }
         if (model.parameters.stream === false) {
           const data = await response.json()
-          subscriber.next(data.choices[0]?.message?.content ?? '')
+          if (transformResponse) {
+            subscriber.next(transformResponse(data))
+          } else {
+            subscriber.next(data.choices[0]?.message?.content ?? '')
+          }
         } else {
           const stream = response.body
           const decoder = new TextDecoder('utf-8')

core/src/types/api/index.ts

@@ -1,3 +1,5 @@
+import { ChatCompletionMessage } from '../inference'
+
 /**
  * Native Route APIs
  * @description Enum of all the routes exposed by the app
@@ -154,3 +156,8 @@ export const APIEvents = [
   ...Object.values(DownloadEvent),
   ...Object.values(LocalImportModelEvent),
 ]
+export type PayloadType = {
+  messages: ChatCompletionMessage[]
+  model: string
+  stream: Boolean
+}

docs/openapi/version.txt

@@ -0,0 +1 @@
+v1.23.2

docs/tests/conftest.py

@@ -0,0 +1,6 @@
+def pytest_collection_modifyitems(items):
+    for item in items:
+        # add the name of the file (without extension) as a marker
+        filename = item.nodeid.split("::")[0].split("/")[-1].replace(".py", "")
+        marker = pytest.mark.file(filename)
+        item.add_marker(marker)

docs/tests/pytest.ini

@@ -0,0 +1,8 @@
+[pytest]
+rp_project = openai-api-test
+rp_launch = OpenAI Collection Test
+rp_launch_description = Full collection to ensure compatibility with OpenAI API
+rp_launch_attributes = 'CI'
+filterwarnings = ignore::pytest.PytestUnknownMarkWarning
+log_format = %(asctime)s %(levelname)s %(message)s
+log_date_format = %Y-%m-%d %H:%M:%S

extensions/inference-cohere-extension/README.md

@@ -0,0 +1,79 @@
+# Cohere Engine Extension
+
+Created using Jan extension example
+
+# Create a Jan Extension using Typescript
+
+Use this template to bootstrap the creation of a TypeScript Jan extension. 🚀
+
+## Create Your Own Extension
+
+To create your own extension, you can use this repository as a template! Just follow the below instructions:
+
+1. Click the Use this template button at the top of the repository
+2. Select Create a new repository
+3. Select an owner and name for your new repository
+4. Click Create repository
+5. Clone your new repository
+
+## Initial Setup
+
+After you've cloned the repository to your local machine or codespace, you'll need to perform some initial setup steps before you can develop your extension.
+
+> [!NOTE]
+>
+> You'll need to have a reasonably modern version of
+> [Node.js](https://nodejs.org) handy. If you are using a version manager like
+> [`nodenv`](https://github.com/nodenv/nodenv) or
+> [`nvm`](https://github.com/nvm-sh/nvm), you can run `nodenv install` in the
+> root of your repository to install the version specified in
+> [`package.json`](./package.json). Otherwise, 20.x or later should work!
+
+1. :hammer_and_wrench: Install the dependencies
+
+   ```bash
+   npm install
+   ```
+
+1. :building_construction: Package the TypeScript for distribution
+
+   ```bash
+   npm run bundle
+   ```
+
+1. :white_check_mark: Check your artifact
+
+   There will be a tgz file in your extension directory now
+
+## Update the Extension Metadata
+
+The [`package.json`](package.json) file defines metadata about your extension, such as
+extension name, main entry, description and version.
+
+When you copy this repository, update `package.json` with the name, description for your extension.
+
+## Update the Extension Code
+
+The [`src/`](./src/) directory is the heart of your extension! This contains the
+source code that will be run when your extension functions are invoked. You can replace the
+contents of this directory with your own code.
+
+There are a few things to keep in mind when writing your extension code:
+
+- Most Jan Extension functions are processed asynchronously.
+  In `index.ts`, you will see that the extension function will return a `Promise<any>`.
+
+  ```typescript
+  import { events, MessageEvent, MessageRequest } from '@janhq/core'
+
+  function onStart(): Promise<any> {
+    return events.on(MessageEvent.OnMessageSent, (data: MessageRequest) =>
+      this.inference(data)
+    )
+  }
+  ```
+
+  For more information about the Jan Extension Core module, see the
+  [documentation](https://github.com/janhq/jan/blob/main/core/README.md).
+
+So, what are you waiting for? Go ahead and start customizing your extension!

extensions/inference-cohere-extension/package.json

@@ -0,0 +1,43 @@
+{
+  "name": "@janhq/inference-cohere-extension",
+  "productName": "Cohere Inference Engine",
+  "version": "1.0.0",
+  "description": "This extension enables Cohere chat completion API calls",
+  "main": "dist/index.js",
+  "module": "dist/module.js",
+  "engine": "cohere",
+  "author": "Jan <service@jan.ai>",
+  "license": "AGPL-3.0",
+  "scripts": {
+    "build": "tsc -b . && webpack --config webpack.config.js",
+    "build:publish": "rimraf *.tgz --glob && yarn build && npm pack && cpx *.tgz ../../pre-install",
+    "sync:core": "cd ../.. && yarn build:core && cd extensions && rm yarn.lock &&  cd inference-cohere-extension && yarn && yarn build:publish"
+  },
+  "exports": {
+    ".": "./dist/index.js",
+    "./main": "./dist/module.js"
+  },
+  "devDependencies": {
+    "cpx": "^1.5.0",
+    "rimraf": "^3.0.2",
+    "webpack": "^5.88.2",
+    "webpack-cli": "^5.1.4",
+    "ts-loader": "^9.5.0"
+  },
+  "dependencies": {
+    "@janhq/core": "file:../../core",
+    "fetch-retry": "^5.0.6",
+    "ulidx": "^2.3.0"
+  },
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "files": [
+    "dist/*",
+    "package.json",
+    "README.md"
+  ],
+  "bundleDependencies": [
+    "fetch-retry"
+  ]
+}

extensions/inference-cohere-extension/resources/models.json

@@ -0,0 +1,26 @@
+  [
+  {
+    "sources": [
+      {
+        "url": "https://cohere.com"
+      }
+    ],
+    "id": "command-r-plus",
+    "object": "model",
+    "name": "Command R+",
+    "version": "1.0",
+    "description": "Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use.",
+    "format": "api",
+    "settings": {},
+    "parameters": {
+      "max_tokens": 128000,
+      "temperature": 0.7,
+      "stream": false
+    },
+    "metadata": {
+      "author": "Cohere",
+      "tags": ["General", "Big Context Length"]
+    },
+    "engine": "cohere"
+  }
+]

extensions/inference-cohere-extension/resources/settings.json

@@ -0,0 +1,23 @@
+[
+  {
+    "key": "chat-completions-endpoint",
+    "title": "Chat Completions Endpoint",
+    "description": "The endpoint to use for chat completions. See the [Cohere API documentation](https://docs.cohere.com/reference/chat) for more information.",
+    "controllerType": "input",
+    "controllerProps": {
+      "placeholder": "https://api.cohere.ai/v1/chat",
+      "value": "https://api.cohere.ai/v1/chat"
+    }
+  },
+  {
+    "key": "cohere-api-key",
+    "title": "API Key",
+    "description": "The Cohere API uses API keys for authentication. Visit your [API Keys](https://platform.openai.com/account/api-keys) page to retrieve the API key you'll use in your requests.",
+    "controllerType": "input",
+    "controllerProps": {
+      "placeholder": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+      "value": "",
+      "type": "password"
+    }
+  }
+]

extensions/inference-cohere-extension/src/index.ts

@@ -0,0 +1,110 @@
+/**
+ * @file This file exports a class that implements the InferenceExtension interface from the @janhq/core package.
+ * The class provides methods for initializing and stopping a model, and for making inference requests.
+ * It also subscribes to events emitted by the @janhq/core package and handles new message requests.
+ * @version 1.0.0
+ * @module inference-openai-extension/src/index
+ */
+
+import { RemoteOAIEngine } from '@janhq/core'
+import { PayloadType } from '@janhq/core'
+import { ChatCompletionRole } from '@janhq/core'
+
+declare const SETTINGS: Array<any>
+declare const MODELS: Array<any>
+
+enum Settings {
+  apiKey = 'cohere-api-key',
+  chatCompletionsEndPoint = 'chat-completions-endpoint',
+}
+
+enum RoleType {
+  user = 'USER',
+  chatbot = 'CHATBOT',
+  system = 'SYSTEM',
+}
+
+type CoherePayloadType = {
+  chat_history?: Array<{ role: RoleType; message: string }>
+  message?: string,
+  preamble?: string,
+}
+
+/**
+ * A class that implements the InferenceExtension interface from the @janhq/core package.
+ * The class provides methods for initializing and stopping a model, and for making inference requests.
+ * It also subscribes to events emitted by the @janhq/core package and handles new message requests.
+ */
+export default class JanInferenceCohereExtension extends RemoteOAIEngine {
+  inferenceUrl: string = ''
+  provider: string = 'cohere'
+
+  override async onLoad(): Promise<void> {
+    super.onLoad()
+
+    // Register Settings
+    this.registerSettings(SETTINGS)
+    this.registerModels(MODELS)
+
+    this.apiKey = await this.getSetting<string>(Settings.apiKey, '')
+    this.inferenceUrl = await this.getSetting<string>(
+      Settings.chatCompletionsEndPoint,
+      ''
+    )
+    if (this.inferenceUrl.length === 0) {
+      SETTINGS.forEach((setting) => {
+        if (setting.key === Settings.chatCompletionsEndPoint) {
+          this.inferenceUrl = setting.controllerProps.value as string
+        }
+      })
+    }
+  }
+
+  onSettingUpdate<T>(key: string, value: T): void {
+    if (key === Settings.apiKey) {
+      this.apiKey = value as string
+    } else if (key === Settings.chatCompletionsEndPoint) {
+      if (typeof value !== 'string') return
+
+      if (value.trim().length === 0) {
+        SETTINGS.forEach((setting) => {
+          if (setting.key === Settings.chatCompletionsEndPoint) {
+            this.inferenceUrl = setting.controllerProps.value as string
+          }
+        })
+      } else {
+        this.inferenceUrl = value
+      }
+    }
+  }
+
+  transformPayload = (payload: PayloadType): CoherePayloadType => {
+    if (payload.messages.length === 0) {
+      return {}
+    }
+    const convertedData:CoherePayloadType = {
+      chat_history: [],
+      message: '',
+    }
+    payload.messages.forEach((item, index) => {
+      // Assign the message of the last item to the `message` property
+      if (index === payload.messages.length - 1) {
+        convertedData.message = item.content as string
+        return
+      }
+      if (item.role === ChatCompletionRole.User) {
+        convertedData.chat_history.push({ role: RoleType.user, message: item.content as string})
+      } else if (item.role === ChatCompletionRole.Assistant) {
+        convertedData.chat_history.push({
+          role: RoleType.chatbot,
+          message: item.content as string,
+        })
+      } else if (item.role === ChatCompletionRole.System) {
+        convertedData.preamble = item.content as string
+      }
+    })
+    return convertedData
+  }
+
+  transformResponse = (data: any) => data.text
+}

extensions/inference-cohere-extension/tsconfig.json

@@ -0,0 +1,14 @@
+{
+  "compilerOptions": {
+    "target": "es2016",
+    "module": "ES6",
+    "moduleResolution": "node",
+    "outDir": "./dist",
+    "esModuleInterop": true,
+    "forceConsistentCasingInFileNames": true,
+    "strict": false,
+    "skipLibCheck": true,
+    "rootDir": "./src"
+  },
+  "include": ["./src"]
+}

extensions/inference-cohere-extension/webpack.config.js

@@ -0,0 +1,37 @@
+const webpack = require('webpack')
+const packageJson = require('./package.json')
+const settingJson = require('./resources/settings.json')
+const modelsJson = require('./resources/models.json')
+
+module.exports = {
+  experiments: { outputModule: true },
+  entry: './src/index.ts', // Adjust the entry point to match your project's main file
+  mode: 'production',
+  module: {
+    rules: [
+      {
+        test: /\.tsx?$/,
+        use: 'ts-loader',
+        exclude: /node_modules/,
+      },
+    ],
+  },
+  plugins: [
+    new webpack.DefinePlugin({
+      MODELS: JSON.stringify(modelsJson),
+      SETTINGS: JSON.stringify(settingJson),
+      ENGINE: JSON.stringify(packageJson.engine),
+    }),
+  ],
+  output: {
+    filename: 'index.js', // Adjust the output file name as needed
+    library: { type: 'module' }, // Specify ESM output format
+  },
+  resolve: {
+    extensions: ['.ts', '.js'],
+  },
+  optimization: {
+    minimize: false,
+  },
+  // Add loaders and other configuration as needed for your project
+}

extensions/inference-nitro-extension/resources/models/phi3-3.8b/model.json

@@ -0,0 +1,32 @@
+{
+    "sources": [
+      {
+        "url": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf",
+        "filename": "Phi-3-mini-4k-instruct-q4.gguf"
+      }
+    ],
+    "id": "phi3-3.8b",
+    "object": "model",
+    "name": "Phi-3 Mini",
+    "version": "1.0",
+    "description": "Phi-3 Mini is Microsoft's newest, compact model designed for mobile use.",
+    "format": "gguf",
+    "settings": {
+      "ctx_len": 4096,
+      "prompt_template": "<|system|>\n{system_message}<|end|>\n<|user|>\n{prompt}<|end|>\n<|assistant|>\n",
+      "llama_model_path": "Phi-3-mini-4k-instruct-q4.gguf"
+    },
+    "parameters": {
+      "max_tokens": 4096,
+      "stop": ["<|end|>"]
+    },
+    "metadata": {
+      "author": "Microsoft",
+      "tags": [
+        "3B",
+        "Finetuned"
+      ],
+      "size": 2320000000
+    },
+    "engine": "nitro"
+  }