Merge branch 'main' into bug/enumeration-chat

Author: urmauur

adr/adr-008-Extensible-Jan-with-Docker.md

@@ -0,0 +1,36 @@
+# ADR 008: Extensible-Jan-with-Docker
+
+## Changelog
+
+- 2023-10-24: Initial draft
+
+## Authors
+
+- @vuonghoainam
+
+## Status
+Proposed
+
+## Context
+
+What is the issue that we're seeing that is motivating this decision or change?
+- The A.I world is moving fast with multiple runtime/ prebaked environment. We or the builder cannot cover just everything but rather we should adopt it and facillitate it as much as possible within Jan.
+- For `Run your own A.I`: Builder can build app on Jan (NodeJS env) and connect to external endpoint which serves the real A.I
+  - e.g 1: Nitro acting as proxy to `triton-inference-server` running within a Docker container controlled by Jan app
+  - e.g 2: Original models can be in many formats (pytorch, paddlepaddle). In order to run it with the most optimized version locally, there must be a step to transpile the model ([Ollama import model](https://github.com/jmorganca/ollama/blob/main/docs/import.md), Tensorrt). Btw Jan can prebuilt it and let user pull but later
+- For `Build your own A.I`: User can fine tune model locally (of course Jan help it with remote but later)
+
+## Decision
+
+What is the change that we're proposing and/or doing?
+- Add Docker client as Core module - [Docker node](https://github.com/apocas/dockerode)
+- 2 example A.I app (adr-002) to demonstrate it and actually use!
+
+## Consequences
+
+What becomes easier or more difficult to do because of this change?
+- We can extend limitlessly :D 
+
+## Alternatives
+
+## Reference

electron/tests/my-models.e2e.spec.ts

@@ -36,11 +36,6 @@ test.afterAll(async () => {
 
 test("shows my models", async () => {
   await page.getByTestId("My Models").first().click();
-  const header = await page
-    .getByRole("heading")
-    .filter({ hasText: "My Models" })
-    .first()
-    .isVisible();
-  expect(header).toBe(false);
+  await page.getByTestId("testid-mymodels-header").isVisible();
   //   More test cases here...
 });

electron/tsconfig.json

@@ -10,9 +10,10 @@
     "noEmitOnError": true,
     "baseUrl": ".",
     "allowJs": true,
+    "skipLibCheck": true,
     "paths": { "*": ["node_modules/*"] },
     "typeRoots": ["node_modules/@types"]
   },
   "include": ["./**/*.ts"],
-  "exclude": ["core", "build", "dist", "tests"]
+  "exclude": ["core", "build", "dist", "tests", "node_modules"]
 }

plugins/inference-plugin/index.ts

@@ -67,7 +67,7 @@ function requestInference(
         }
         subscriber.complete();
       })
-      .catch(subscriber.error);
+      .catch((err) => subscriber.error(err));
   });
 }
 
@@ -143,7 +143,8 @@ async function handleMessageRequest(data: NewMessageRequest) {
     },
     error: async (err) => {
       message.message =
-        message.message.trim() + "\n" + "Error occurred: " + err;
+        message.message.trim() + "\n" + "Error occurred: " + err.message;
+      events.emit(EventName.OnMessageResponseUpdate, message);
       // TODO: Common collections should be able to access via core functions instead of store
       await store.updateOne("messages", message._id, message);
     },

plugins/inference-plugin/module.ts

@@ -14,53 +14,49 @@ const initModel = (fileName) => {
       if (!fileName) {
         reject("Model not found, please download again.");
       }
-      if (subprocess) {
-        console.error("A subprocess is already running. Attempt to kill then reinit.");
-        killSubprocess();
-      }
       resolve(fileName);
     })
-      // Kill port process if it is already in use
-      .then((fileName) =>
-        tcpPortUsed
-          .waitUntilFree(PORT, 200, 3000)
-          .catch(() => killPortProcess(PORT))
-          .then(() => fileName)
-      )
       // Spawn Nitro subprocess to load model
       .then(() => {
-        let binaryFolder = path.join(__dirname, "nitro"); // Current directory by default
-        let binaryName;
+        return tcpPortUsed.check(PORT, "127.0.0.1").then((inUse) => {
+          if (!inUse) {
+            let binaryFolder = path.join(__dirname, "nitro"); // Current directory by default
+            let binaryName;
 
-        if (process.platform === "win32") {
-          // Todo: Need to check for CUDA support to switch between CUDA and non-CUDA binaries
-          binaryName = "nitro_start_windows.bat";
-        } else if (process.platform === "darwin") {
-          // Mac OS platform
-          binaryName = process.arch === "arm64" ? "nitro_mac_arm64" : "nitro_mac_intel";
-        } else {
-          // Linux
-          // Todo: Need to check for CUDA support to switch between CUDA and non-CUDA binaries
-          binaryName = "nitro_start_linux.sh"; // For other platforms
-        }
+            if (process.platform === "win32") {
+              // Todo: Need to check for CUDA support to switch between CUDA and non-CUDA binaries
+              binaryName = "nitro_start_windows.bat";
+            } else if (process.platform === "darwin") {
+              // Mac OS platform
+              binaryName =
+                process.arch === "arm64"
+                  ? "nitro_mac_arm64"
+                  : "nitro_mac_intel";
+            } else {
+              // Linux
+              // Todo: Need to check for CUDA support to switch between CUDA and non-CUDA binaries
+              binaryName = "nitro_start_linux.sh"; // For other platforms
+            }
 
-        const binaryPath = path.join(binaryFolder, binaryName);
+            const binaryPath = path.join(binaryFolder, binaryName);
 
-        // Execute the binary
-        subprocess = spawn(binaryPath, { cwd: binaryFolder });
+            // Execute the binary
+            subprocess = spawn(binaryPath, { cwd: binaryFolder });
 
-        // Handle subprocess output
-        subprocess.stdout.on("data", (data) => {
-          console.log(`stdout: ${data}`);
-        });
+            // Handle subprocess output
+            subprocess.stdout.on("data", (data) => {
+              console.log(`stdout: ${data}`);
+            });
 
-        subprocess.stderr.on("data", (data) => {
-          console.error(`stderr: ${data}`);
-        });
+            subprocess.stderr.on("data", (data) => {
+              console.error(`stderr: ${data}`);
+            });
 
-        subprocess.on("close", (code) => {
-          console.log(`child process exited with code ${code}`);
-          subprocess = null;
+            subprocess.on("close", (code) => {
+              console.log(`child process exited with code ${code}`);
+              subprocess = null;
+            });
+          }
         });
       })
       .then(() => tcpPortUsed.waitUntilUsed(PORT, 300, 30000))

plugins/inference-plugin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@janhq/inference-plugin",
-  "version": "1.0.13",
+  "version": "1.0.14",
   "description": "Inference Plugin, powered by @janhq/nitro, bring a high-performance Llama model inference in pure C++.",
   "icon": "https://raw.githubusercontent.com/tailwindlabs/heroicons/88e98b0c2b458553fbadccddc2d2f878edc0387b/src/20/solid/command-line.svg",
   "main": "dist/index.js",

web/app/_components/ConversationalList/index.tsx

@@ -14,7 +14,7 @@ const ConversationalList: React.FC<Props> = ({ models }) => (
       </span>
     </div>
     <div className="scroll mt-2 flex w-full gap-2 overflow-hidden overflow-x-scroll pl-6">
-      {models.map((item) => (
+      {models?.map((item) => (
         <ConversationalCard key={item._id} model={item} />
       ))}
     </div>

web/app/_components/CreateBotContainer/index.tsx

@@ -13,15 +13,14 @@ import DraggableProgressBar from '../DraggableProgressBar'
 import { useSetAtom } from 'jotai'
 import { activeBotAtom } from '@helpers/atoms/Bot.atom'
 import {
-  leftSideBarExpandStateAtom,
   rightSideBarExpandStateAtom,
 } from '@helpers/atoms/SideBarExpand.atom'
 import {
   MainViewState,
   setMainViewStateAtom,
 } from '@helpers/atoms/MainView.atom'
-import { executeSerial } from '../../../../electron/core/plugin-manager/execution/extension-manager'
 import { DataService } from '@janhq/core'
+import { executeSerial } from '@services/pluginService'
 
 const CreateBotContainer: React.FC = () => {
   const { downloadedModels } = useGetDownloadedModels()

web/app/_components/HistoryItem/index.tsx

@@ -1,7 +1,6 @@
 import React from 'react'
 import { useAtomValue, useSetAtom } from 'jotai'
 import { ModelManagementService } from '@janhq/core'
-import { executeSerial } from '../../../../electron/core/plugin-manager/execution/extension-manager'
 import {
   getActiveConvoIdAtom,
   setActiveConvoIdAtom,
@@ -13,6 +12,7 @@ import {
 } from '@helpers/atoms/MainView.atom'
 import { displayDate } from '@utils/datetime'
 import { twMerge } from 'tailwind-merge'
+import { executeSerial } from '@services/pluginService'
 
 type Props = {
   conversation: Conversation

web/app/_components/LeftRibbonNav/index.tsx

@@ -59,7 +59,7 @@ const LeftRibbonNav: React.FC = () => {
 
   const onBotListClick = async () => {
     const bots = await getAllBots()
-    if (bots.length === 0) {
+    if (bots?.length === 0) {
       alert('You have no bot')
       return
     }