Add docs

Signed-off-by: Daishan Peng <[email protected]>

docs/.gitignore

@@ -0,0 +1,20 @@
+# Dependencies
+/node_modules
+
+# Production
+/build
+
+# Generated files
+.docusaurus
+.cache-loader
+
+# Misc
+.DS_Store
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*

docs/README.md

@@ -0,0 +1,41 @@
+# Website
+
+This website is built using [Docusaurus](https://docusaurus.io/), a modern static website generator.
+
+### Installation
+
+```
+$ yarn
+```
+
+### Local Development
+
+```
+$ yarn start
+```
+
+This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
+
+### Build
+
+```
+$ yarn build
+```
+
+This command generates static content into the `build` directory and can be served using any static contents hosting service.
+
+### Deployment
+
+Using SSH:
+
+```
+$ USE_SSH=true yarn deploy
+```
+
+Not using SSH:
+
+```
+$ GIT_USER=<Your GitHub username> yarn deploy
+```
+
+If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

docs/babel.config.js

@@ -0,0 +1,3 @@
+module.exports = {
+  presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
+};

docs/docs/01-overview.md

@@ -0,0 +1,16 @@
+---
+title: Overview
+slug: /
+---
+
+[![Discord](https://img.shields.io/discord/1204558420984864829?label=Discord)](https://discord.gg/9sSf4UyAMC)
+
+<img alt="Knowledge Logo" src="img/logo.png" style={{width: 400}}/>
+
+**Mail-Assistant** is an AI-powered application that can help you check others' availability and send email invites. It leverages [GPTScript](https://docs.gptscript.ai/) to provide a chatbot interface through a UI to assist you with various O365 tasks.
+
+It has the following features:
+
+1. Integrates with Microsoft Azure OAuth to assist users with office tasks.
+2. Provides a task management system to help users manage tasks and chat sessions.
+3. Offers customization of each task with different contexts and rulesets.

docs/docs/02-installation.md

@@ -0,0 +1,137 @@
+# Installation
+
+### Create Microsoft App Registration
+
+Follow the [instructions](https://learn.microsoft.com/en-us/entra/identity-platform/quickstart-register-app?tabs=certificate) here.
+
+After creating the app, [create a secret](https://learn.microsoft.com/en-us/entra/identity-platform/quickstart-register-app?tabs=certificate#add-credentials) and copy the secret value.
+
+Make sure you obtain the following values that are needed in the next step:
+
+| Key           | Description             |
+|---------------|-------------------------|
+| CLIENT_ID     | Microsoft client ID     |
+| CLIENT_SECRET | Microsoft client secret |
+| TENANT_ID     | Microsoft tenant ID     |
+
+:::note
+
+Make sure the Redirect URL is configured to `http://localhost:8080`. This ensures Microsoft will redirect to the localhost server (which is where the Copilot server listens) and complete the OAuth workflow.
+
+:::
+
+### Prepare Other Environment Variables
+
+| Key               | Description                                                                                                               |
+|-------------------|---------------------------------------------------------------------------------------------------------------------------|
+| OPENAI_API_KEY    | Provide your OPENAI_API_KEY.                                                                                              |
+| MICROSOFT_JWT_KEY | Provide a secret value used as a JWT key. This is used to sign JWT tokens issued on behalf of a user. Keep this a secret. |                                                                                       
+| PUBLIC_URL        | Public URL that your local server is listening to.                                                                        |
+
+:::note
+
+Since everything is running locally, you need to expose your app server publicly so that webhook events can be delivered to the app. The easiest way is to run `ngrok`. Check the docs on [ngrok](https://ngrok.com/docs/getting-started/) on how to forward your local port publicly.
+
+:::
+
+:::note
+
+You can use `openssl rand -base64 32` to generate a random value for the JWT secret key.
+
+:::
+
+### Running with Docker Compose
+
+Use the docker-compose file below with the .env file.
+
+```yaml
+version: '3.8'
+
+services:
+  db:
+    image: postgres:12-alpine
+    container_name: postgres_db
+    environment:
+      POSTGRES_DB: ${DB_NAME}
+      POSTGRES_USER: ${DB_USER}
+      POSTGRES_PASSWORD: ${DB_PASSWORD}
+    ports:
+      - "5432"
+    volumes:
+      - db_data:/var/lib/postgresql/data
+    env_file:
+      - .env
+    restart: always
+
+  ui:
+    image: "ghcr.io/gptscript-ai/mail-assistant/ui:latest"
+    ports:
+      - "3000"
+    restart: always
+
+  server:
+    image: "ghcr.io/gptscript-ai/mail-assistant/server:latest"
+    ports:
+      - "8080:8080"
+    restart: always
+    environment:
+      MICROSOFT_CLIENT_ID: ${MICROSOFT_CLIENT_ID}
+      MICROSOFT_CLIENT_SECRET: ${MICROSOFT_CLIENT_SECRET}
+      MICROSOFT_JWT_KEY: ${MICROSOFT_JWT_KEY}
+      MICROSOFT_TENANT_ID: ${MICROSOFT_TENANT_ID}
+      PG_DBNAME: ${DB_NAME}
+      PG_HOST: ${DB_HOST}
+      PG_USER: ${DB_USER}
+      PG_PASSWORD: ${DB_PASSWORD}
+      PUBLIC_URL: ${PUBLIC_URL}
+      UI_SERVER: ${UI_SERVER}
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      DEVELOPMENT: "true"
+    env_file:
+      - .env
+
+volumes:
+  db_data:
+```
+
+Replace the .env placeholder with the values you obtained in the previous step.
+
+```
+DB_NAME=copilot
+DB_USER=admin
+DB_PASSWORD=admin123
+DB_HOST=db
+
+MICROSOFT_CLIENT_ID=${CLIENT_ID}
+OPENAI_API_KEY=${OPENAI_API_KEY}
+MICROSOFT_CLIENT_SECRET=${CLIENT_SECRET}
+MICROSOFT_JWT_KEY=${JWT_SECRET_KEY}
+MICROSOFT_TENANT_ID=${TENANT_ID}
+
+DEVELOPMENT=true
+
+PUBLIC_URL=${PUBLIC_URL}
+UI_SERVER=http://ui:3000
+```
+
+Then run docker-compose:
+
+```bash
+docker compose up -d
+```
+
+Go to `http://localhost:8080` and you can start logging in and using the app.
+
+---
+
+### Use Other LLM
+
+The default model is `gpt-4o`. To use a different OpenAI model, update the `DEFAULT_MODEL` in the `.env` file.
+
+To connect to an OpenAI-compatible local model server, such as llama.cpp, ollama, or Rubra's tool.cpp, update the `OPENAI_API_KEY`, `OPENAI_BASE_URL`, and `DEFAULT_MODEL` accordingly. For example:
+
+```
+OPENAI_API_KEY=sk-123
+OPENAI_BASE_URL=http://host.docker.internal:1234/v1
+DEFAULT_MODEL=rubra-meta-llama-3-8b-instruct.Q8_0.gguf
+```

docs/docs/03-guide.md

@@ -0,0 +1,58 @@
+# Guide
+
+First, you need to sign in to the app using Microsoft OAuth.
+
+Click on the link to sign in, and you will be redirected to the Microsoft OAuth page, where you need to agree to grant permission to this app.
+
+## Exploring the Dashboard
+
+Once you are signed in, you will land on the Dashboard page. It mainly has two resources:
+
+- **Tasks**
+
+  Tasks allow you to create and manage tasks. Each task maintains its own chat session, helping you with some O365 tasks with the chatbot. It can be paused and resumed at any time, keeping the chat history and session.
+
+- **Rule Sets**
+
+  Rule sets allow you to define rules for each task. It is basically adding more context to the chat session. You can create a rule like "When meeting with X, always meet in the afternoon" and attach it to a task. When the task runs, it will remember the rule you gave when you interact with it.
+
+## Creating Tasks
+
+1. Click on `Tasks` on the left panel.
+2. Click on `Add`. Fill in the name, description, and additional rules (if any).
+
+:::note
+
+You can attach pre-configured rule sets to your task.
+
+:::
+
+## Creating Rule Sets
+
+You can create pre-configured rule sets and attach them to a task.
+
+1. Click on `Rule Sets` on the left panel.
+2. Click on `Add`.
+
+## Running a Task
+
+Simply click on the task name to start running a task in a chat session.
+
+## Automatic Task Creation
+
+The `Mail-Assistant` app watches your inbox and detects if other people want to meet with you. If so, it will automatically create a task and remind you that you can start scheduling a meeting with them.
+
+You can see the notification from the app once a new task is created.
+
+## Cold Email Detection
+
+:::warning
+
+This feature is currently experimental.
+
+:::
+
+`Mail-Assistant` can help you detect cold emails for marketing and move them to a `Cold Email` folder. To enable it:
+
+1. Go to `Accounts` and enable `Cold Email Detection`.
+2. Any email marked as a cold email will appear under `Cold Email`. You can move it back to the inbox if it has been falsely detected.

docs/docs/04-demo.md

@@ -0,0 +1,3 @@
+# Demo
+
+Here is a quick [demo](https://www.loom.com/share/ff3aefb360214ee59bbc1c756da2c313) on how to create and run tasks, and also schedule meetings in the chatbot.

docs/docusaurus.config.js

@@ -0,0 +1,98 @@
+// @ts-check
+// `@type` JSDoc annotations allow editor autocompletion and type checking
+// (when paired with `@ts-check`).
+// There are various equivalent ways to declare your Docusaurus config.
+// See: https://docusaurus.io/docs/api/docusaurus-config
+
+import { themes as prismThemes } from "prism-react-renderer";
+
+/** @type {import('@docusaurus/types').Config} */
+const config = {
+  title: "Mail-Assistant Docs",
+  tagline: "Welcome to the Mail-Assistant Docs",
+  favicon: "img/favicon.ico",
+  baseUrl: "/mail-assistant/",
+  url: "https://gptscript-ai.github.io",
+  organizationName: "gptscript-ai",
+  projectName: "mail-assistant",
+  onBrokenLinks: "throw",
+  onBrokenMarkdownLinks: "warn",
+  trailingSlash: false,
+
+  i18n: {
+    defaultLocale: "en",
+    locales: ["en"],
+  },
+
+  presets: [
+    [
+      "classic",
+      /** @type {import('@docusaurus/preset-classic').Options} */
+      ({
+        docs: {
+          sidebarPath: "./sidebars.js",
+          editUrl: "https://github.com/gptscript-ai/mail-assistant/tree/main/docs/",
+          routeBasePath: "/", // Serve the docs at the site's root
+          showLastUpdateTime: true,
+        },
+        theme: {
+          customCss: "./src/css/custom.css",
+        },
+        blog: false,
+      }),
+    ],
+  ],
+
+  themeConfig:
+    /** @type {import('@docusaurus/preset-classic').ThemeConfig} */
+    ({
+      // Replace with your project's social card
+      image: "img/docusaurus-social-card.jpg",
+      navbar: {
+        title: "Mail-Assistant",
+        style: "dark",
+        logo: {
+          alt: "Mail-Assistant Logo",
+          src: "img/logo.png",
+        },
+        items: [
+          {
+            href: "https://github.com/gptscript-ai/mail-assistant",
+            label: "GitHub",
+            position: "right",
+          },
+          {
+            href: "https://discord.gg/9sSf4UyAMC",
+            label: "Discord",
+            position: "right",
+          },
+        ],
+      },
+      footer: {
+        style: "dark",
+        links: [
+          {
+            label: "GitHub",
+            to: "https://github.com/gptscript-ai/mail-assistant",
+          },
+          {
+            label: "Discord",
+            to: "https://discord.gg/9sSf4UyAMC",
+          },
+        ],
+        copyright: `Copyright © ${new Date().getFullYear()} Acorn Labs, Inc`,
+      },
+      prism: {
+        theme: prismThemes.github,
+        darkTheme: prismThemes.dracula,
+        additionalLanguages: ["cue", "docker"],
+      },
+      // algolia: {
+      //   apiKey: "c886c827d4057d15ab11efbc59b94a49",
+      //   appId: "CLLI98NP9G",
+      //   indexName: "gptscript",
+      // },
+    }),
+};
+
+export default config;