Add content creation workflow using Motia

motia-content-creation/.env.example

@@ -0,0 +1,4 @@
+OPENAI_API_KEY=your_openai_api_key
+FIRECRAWL_API_KEY=your_firecrawl_api_key
+TYPEFULLY_API_KEY=your_typefully_api_key
+MOTIA_PORT=3000

motia-content-creation/.gitignore

@@ -0,0 +1,109 @@
+# Dependencies
+.motia
+node_modules/
+python_modules/
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Python dependencies and environments
+__pycache__/
+*.py[cod]
+*.egg-info/
+.venv/
+venv/
+Pipfile.lock
+.mypy_cache/
+.pytest_cache/
+
+# Environment variables
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# Build outputs
+dist/
+build/
+*.tsbuildinfo
+
+# Logs
+logs
+*.log
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Coverage directory used by tools like istanbul
+coverage/
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Dependency directories
+jspm_packages/
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+public
+
+# Storybook build outputs
+.out
+.storybook-out
+
+# Temporary folders
+tmp/
+temp/
+
+# Editor directories and files
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db

motia-content-creation/README.md

@@ -0,0 +1,121 @@
+# Social Media Automation workflow using Motia
+
+A streamlined content generation agent built with [Motia](https://motia.dev) that transforms articles into engaging Twitter threads and LinkedIn posts using AI.
+
+We use the following tech stack:
+- Motia as the unified backend framework
+- Firecrawl to scrape web content
+- OpenAI for agentic capabilities
+
+## 🎯Overview
+
+**Workflow**
+
+Our workflow consists of 4 main steps:-
+
+```
+API → Scrape → Generate → Schedule
+```
+
+1. **API**: Receives article URL via POST request
+2. **Scrape**: Extracts content using Firecrawl in markdown format
+3. **Generate**: Creates Twitter & LinkedIn content using OpenAI
+4. **Schedule**: Saves content as drafts in Typefully for review
+
+## 🛠️ Setup
+
+### Prerequisites
+
+- Node.js 18+
+- Python 3.x
+- API keys for:
+  - OpenAI
+  - Firecrawl
+  - Typefully
+
+### Installation
+
+1. **Install dependencies:**
+   ```bash
+   npm install or pnpm install
+   ```
+
+3. **Configure environment:**
+   ```bash
+   cp .env.example .env
+   # Edit .env with your API keys
+   ```
+   or Create a `.env` file in the root directory with the following variables:
+   ```bash
+    OPENAI_API_KEY=your_openai_api_key
+    FIRECRAWL_API_KEY=your_firecrawl_api_key
+    TYPEFULLY_API_KEY=your_typefully_api_key
+   ```
+
+4. **Start the development server:**
+   ```bash
+   npm run dev
+   ```
+
+## 🚀 Usage
+
+### Generate Content
+
+Send a POST request to trigger content generation:
+
+```bash
+curl -X POST http://localhost:3000/generate-content \\
+  -H "Content-Type: application/json" \\
+  -d '{"url": "https://example.com/article"}'
+```
+
+**Response:**
+```json
+{
+  "message": "Content generation started",
+  "requestId": "req_123456",
+  "url": "https://example.com/article",
+  "status": "processing"
+}
+```
+
+### View Results
+
+After processing completes:
+1. Visit [Typefully](https://typefully.com/drafts)
+2. Review your generated Twitter thread and LinkedIn post
+3. Edit if needed and publish!
+
+## 📁 Project Structure
+
+```
+social-media-automation/
+├── steps/
+│   ├── api.step.ts          # API endpoint handler
+│   ├── scrape.step.ts       # Firecrawl integration
+│   ├── generate.step.ts     # Parallel OpenAI calls
+│   └── schedule.step.ts     # Typefully scheduling
+├── prompts/
+│   ├── twitter-prompt.txt   # Twitter generation prompt
+│   └── linkedin-prompt.txt  # LinkedIn generation prompt
+├── config/
+│   └── index.js            # Configuration management
+├── package.json
+├── tsconfig.json
+└── README.md
+```
+
+## 🔍 Monitoring
+
+The Motia workbench provides an interactive UI where you can easily deb ug and monitor your flows as interactive diagrams. It runs automatically with the development server.
+
+## 📬 Stay Updated with Our Newsletter!
+**Get a FREE Data Science eBook** 📖 with 150+ essential lessons in Data Science when you subscribe to our newsletter! Stay in the loop with the latest tutorials, insights, and exclusive resources. [Subscribe now!](https://join.dailydoseofds.com)
+
+[![Daily Dose of Data Science Newsletter](https://github.com/patchy631/ai-engineering/blob/main/resources/join_ddods.png)](https://join.dailydoseofds.com)
+
+---
+
+## Contribution
+
+Contributions are welcome! Please fork the repository and submit a pull request with your improvements. 

motia-content-creation/config/index.js

@@ -0,0 +1,33 @@
+require('dotenv').config();
+
+const config = {
+  openai: {
+    apiKey: process.env.OPENAI_API_KEY,
+    model: 'gpt-4o',
+  },
+
+  firecrawl: {
+    apiKey: process.env.FIRECRAWL_API_KEY,
+  },
+
+  typefully: {
+    apiKey: process.env.TYPEFULLY_API_KEY,
+  },
+
+  motia: {
+    port: parseInt(process.env.MOTIA_PORT) || 3000,
+  },
+
+  validate() {
+    const required = ['OPENAI_API_KEY', 'FIRECRAWL_API_KEY', 'TYPEFULLY_API_KEY'];
+    const missing = required.filter(key => !process.env[key]);
+
+    if (missing.length > 0) {
+      throw new Error(`Missing required environment variables: ${missing.join(', ')}`);
+    }
+  }
+};
+
+config.validate();
+
+module.exports = config;

motia-content-creation/package.json

@@ -0,0 +1,34 @@
+{
+  "name": "social-media-automation",
+  "description": "AI-powered social media automation workflow that scrapes articles and generates viral social media posts using Motia",
+  "scripts": {
+    "prepare": "python3 -m venv python_modules && source python_modules/bin/activate && pip install -r requirements.txt",
+    "dev": "source python_modules/bin/activate && motia dev",
+    "dev:debug": "source python_modules/bin/activate && motia dev --debug",
+    "build": "source python_modules/bin/activate && motia build",
+    "clean": "rm -rf dist .motia .mermaid node_modules python_modules",
+    "generate:config": "motia get-config --output ./"
+  },
+  "keywords": [
+    "motia",
+    "ai",
+    "content-writing",
+    "social-media",
+    "automation",
+    "web-scraping"
+  ],
+  "dependencies": {
+    "motia": "^0.4.0-beta.90",
+    "@mendable/firecrawl-js": "^1.0.0",
+    "openai": "^4.90.0",
+    "dotenv": "^16.5.0",
+    "zod": "^3.25.67",
+    "axios": "^1.10.0"
+  },
+  "devDependencies": {
+    "@types/node": "^20.17.28",
+    "@types/react": "^18.3.23",
+    "ts-node": "^10.9.2",
+    "typescript": "^5.8.3"
+  }
+}

motia-content-creation/prompts/linkedin-prompt.txt

@@ -0,0 +1,64 @@
+As a technical writing assistant, your task is to understand the writing style, paraphrasing, and spacing of the example post provided below. 
+
+Create a post based on the article content that follows this example, ensure your responses sound genuine and aim to convey valuable information.
+
+Be precise, so that it's easier for readers to grasp the essence of the post in minimal time.
+
+You should sound genuine and informative.
+
+Keep the points (if any) succinct and precise so that it can be a better reading experience for all users, whether they're reading it on mobile or on web.
+
+###############################
+
+Example LinkedIn Post:
+
+Python is all you need.
+
+No other language will give you a better bang for your buck. No other language will let you do more.
+
+Today, you can build AI and data applications using Python alone!
+
+Take a look at Taipy, an open-source Python library to build end-to-end production applications:
+
+https://github.com/Avaiga/taipy
+
+Star the repo!
+
+You can use Taipy to build production-ready applications. Some of its perks:
+
+- Taipy scales as more users hit your application
+• Taipy can work with huge datasets
+• Taipy is multi-user and can manage different user profiles
+
+Taipy has a library of pre-built components for interacting with data pipelines, including visualization and management tools. It also supports tools for versioning and pipeline orchestration.
+
+It's open-source and comes with a Visual Studio Code extension that allows you to start without writing any code.
+
+For enterprise customers, Taipy Designer is a drag-and-drop layer that helps build applications using a visual interface.
+
+Taipy's goal is not to replace web developers but to provide an alternative to those who need to build applications without web experience. If you are a data scientist or someone dealing with data, Taipy will simplify your life considerably.
+
+###############################
+
+Based on the example above, analyze the following article content and create a LinkedIn post that follows the same style, tone, and structure. Focus on:
+
+1. **Strong Opening**: Start with a compelling statement or hook
+2. **Value Proposition**: Clearly communicate what the reader will gain
+3. **Practical Information**: Include actionable insights or tools
+4. **Professional Tone**: Maintain a balance between casual and professional
+5. **Bullet Points**: Use them for easy scanning and readability
+6. **Call-to-Action**: End with engagement or next steps
+7. **Genuine Voice**: Sound authentic and knowledgeable
+
+**Article Title**: {{title}}
+
+**Article Content**: 
+{{content}}
+
+Generate a LinkedIn post based on this content. Make it informative, engaging, and valuable for a professional audience interested in technology, AI, and career development.
+
+Return your response in the following JSON format:
+{
+  "post": "Your complete LinkedIn post content here",
+  "characterCount": 1250
+}