patchy631 · xpander-ai-coding-agent · Aug 7, 2025 · coderabbitai · Aug 7, 2025
diff --git a/ai_news_generator/README.md b/ai_news_generator/README.md
@@ -1,21 +1,164 @@
 
-# AI News generator
+# AI News Generator
 
-This project leverages CrewAI and Cohere's Command-R:7B model to build an AI news generator!
+This project leverages **CrewAI Flows** and Cohere's Command-R:7B model to build a modular, agentic AI news generator! 
+
+The application has been refactored to use CrewAI's new Flow-based architecture, providing better modularity, state management, and workflow orchestration.
+
+## ✨ Features
+
+- **Flow-Based Architecture**: Built using CrewAI Flows with `@start` and `@listen` decorators
+- **Two-Phase Workflow**: Research phase followed by content writing phase
+- **Modular Design**: Separate agents for research and content writing
+- **State Management**: Proper state handling between workflow phases
+- **Multiple Interfaces**: Both CLI and Streamlit web interface
+- **Structured Output**: Well-formatted markdown blog posts with citations
+
+## 🏗️ Architecture
+
+The application uses a **Flow-based architecture** with two main phases:
+
+```
+┌─────────────────┐    @start     ┌─────────────────┐
+│  Research Phase │──────────────▶│  Writing Phase  │
+│                 │    @listen    │                 │
+├─────────────────┤               ├─────────────────┤
+│ • Web search    │               │ • Content       │
+│ • Fact checking │               │   generation    │
+│ • Source        │               │ • Formatting    │
+│   validation    │               │ • Citations     │
+└─────────────────┘               └─────────────────┘
+```
+
+### Core Components
+
+- **`NewsGeneratorFlow`**: Main Flow class orchestrating the workflow
+- **Research Agent**: Senior Research Analyst for comprehensive research
+- **Writing Agent**: Content Writer for transforming research into engaging content
+- **State Management**: Pydantic models for structured data flow
 
 ## Installation and setup
 
 **Get API Keys**:
    - [Serper API Key](https://serper.dev/)
    - [Cohere API Key](https://dashboard.cohere.com/api-keys)
 
-
 **Install Dependencies**:
    Ensure you have Python 3.11 or later installed.
    ```bash
-   pip install crewai crewai-tools
+   pip install crewai crewai-tools streamlit python-dotenv
+   ```
+
+**Environment Setup**:
+   Create a `.env` file in the project directory:
+   ```env
+   SERPER_API_KEY=your_serper_api_key_here
+   COHERE_API_KEY=your_cohere_api_key_here
    ```
 
+## 🚀 Usage
+
+### Command Line Interface
+
+Run the flow directly from the command line:
+
+```bash
+# Basic usage
+python main.py --topic "Latest developments in artificial intelligence"
+
+# Save to file
+python main.py --topic "Climate change solutions" --output article.md
+
+# Verbose mode
+python main.py --topic "Blockchain innovations" --verbose
+```
+
+### Streamlit Web Interface
+
+Launch the interactive web interface:
+
+```bash
+streamlit run app.py
+```
+
+Then open your browser to the displayed URL (typically `http://localhost:8501`).
+
+### Programmatic Usage
+
+Use the flow in your own Python code:
+
+```python
+from news_flow import NewsGeneratorFlow
+
+# Create and run the flow
+flow = NewsGeneratorFlow()
+result = flow.kickoff(inputs={"topic": "Your topic here"})
+print(result)
+
+# Or use the convenience function
+from news_flow import generate_content_with_flow
+
+content = generate_content_with_flow("Your topic here")
+print(content)
+```
+
+## 🔧 Flow Implementation Details
+
+### Flow Structure
+
+The `NewsGeneratorFlow` class implements the CrewAI Flow pattern:
+
+```python
+class NewsGeneratorFlow(Flow[ResearchState]):
+    @start()
+    def research_phase(self) -> str:
+        # Initial research using Senior Research Analyst
+
+    @listen(research_phase)
+    def writing_phase(self, research_results: str) -> str:
+        # Content writing using research results
+```
+
+### State Management
+
+The flow uses structured state management with Pydantic models:
+
+```python
+class ResearchState(BaseModel):
+    topic: str
+    research_brief: str
+    sources: list[str] = []
+    key_findings: list[str] = []
+```
+
+### Agent Specialization
+
+- **Senior Research Analyst**: Handles web research, fact-checking, and source validation
+- **Content Writer**: Transforms research into engaging, well-structured blog content
+
+## 🧪 Testing
+
+Test the basic functionality:
+
+```bash
+# Test the flow with a simple topic
+python main.py --topic "Python programming" --verbose
+
+# Test the web interface
+streamlit run app.py
+```
+
+## 📁 Project Structure
+
+```
+ai_news_generator/
+├── app.py              # Streamlit web interface
+├── main.py            # CLI entry point
+├── news_flow.py       # Core Flow implementation
+├── README.md          # This file
+└── .env              # Environment variables (create this)
+```
+
 ---
 
 ## 📬 Stay Updated with Our Newsletter!

diff --git a/ai_news_generator/__pycache__/app.cpython-311.pyc b/ai_news_generator/__pycache__/app.cpython-311.pyc
diff --git a/ai_news_generator/__pycache__/main.cpython-311.pyc b/ai_news_generator/__pycache__/main.cpython-311.pyc
diff --git a/ai_news_generator/__pycache__/news_flow.cpython-311.pyc b/ai_news_generator/__pycache__/news_flow.cpython-311.pyc
diff --git a/ai_news_generator/app.py b/ai_news_generator/app.py
@@ -1,7 +1,6 @@
 import os
 import streamlit as st
-from crewai import Agent, Task, Crew, LLM
-from crewai_tools import SerperDevTool
+from news_flow import generate_content_with_flow
 from dotenv import load_dotenv
 
 # Load environment variables
@@ -46,101 +45,10 @@
         """)
 
 def generate_content(topic):
-    llm = LLM(
-        model="command-r",
-        temperature=0.7
-    )
-
-    search_tool = SerperDevTool(n_results=10)
-
-    # First Agent: Senior Research Analyst
-    senior_research_analyst = Agent(
-        role="Senior Research Analyst",
-        goal=f"Research, analyze, and synthesize comprehensive information on {topic} from reliable web sources",
-        backstory="You're an expert research analyst with advanced web research skills. "
-                "You excel at finding, analyzing, and synthesizing information from "
-                "across the internet using search tools. You're skilled at "
-                "distinguishing reliable sources from unreliable ones, "
-                "fact-checking, cross-referencing information, and "
-                "identifying key patterns and insights. You provide "
-                "well-organized research briefs with proper citations "
-                "and source verification. Your analysis includes both "
-                "raw data and interpreted insights, making complex "
-                "information accessible and actionable.",
-        allow_delegation=False,
-        verbose=True,
-        tools=[search_tool],
-        llm=llm
-    )
-
-    # Second Agent: Content Writer
-    content_writer = Agent(
-        role="Content Writer",
-        goal="Transform research findings into engaging blog posts while maintaining accuracy",
-        backstory="You're a skilled content writer specialized in creating "
-                "engaging, accessible content from technical research. "
-                "You work closely with the Senior Research Analyst and excel at maintaining the perfect "
-                "balance between informative and entertaining writing, "
-                "while ensuring all facts and citations from the research "
-                "are properly incorporated. You have a talent for making "
-                "complex topics approachable without oversimplifying them.",
-        allow_delegation=False,
-        verbose=True,
-        llm=llm
-    )
-
-    # Research Task
-    research_task = Task(
-        description=("""
-            1. Conduct comprehensive research on {topic} including:
-                - Recent developments and news
-                - Key industry trends and innovations
-                - Expert opinions and analyses
-                - Statistical data and market insights
-            2. Evaluate source credibility and fact-check all information
-            3. Organize findings into a structured research brief
-            4. Include all relevant citations and sources
-        """),
-        expected_output="""A detailed research report containing:
-            - Executive summary of key findings
-            - Comprehensive analysis of current trends and developments
-            - List of verified facts and statistics
-            - All citations and links to original sources
-            - Clear categorization of main themes and patterns
-            Please format with clear sections and bullet points for easy reference.""",
-        agent=senior_research_analyst
-    )
-
-    # Writing Task
-    writing_task = Task(
-        description=("""
-            Using the research brief provided, create an engaging blog post that:
-            1. Transforms technical information into accessible content
-            2. Maintains all factual accuracy and citations from the research
-            3. Includes:
-                - Attention-grabbing introduction
-                - Well-structured body sections with clear headings
-                - Compelling conclusion
-            4. Preserves all source citations in [Source: URL] format
-            5. Includes a References section at the end
-        """),
-        expected_output="""A polished blog post in markdown format that:
-            - Engages readers while maintaining accuracy
-            - Contains properly structured sections
-            - Includes Inline citations hyperlinked to the original source url
-            - Presents information in an accessible yet informative way
-            - Follows proper markdown formatting, use H1 for the title and H3 for the sub-sections""",
-        agent=content_writer
-    )
-
-    # Create Crew
-    crew = Crew(
-        agents=[senior_research_analyst, content_writer],
-        tasks=[research_task, writing_task],
-        verbose=True
-    )
-
-    return crew.kickoff(inputs={"topic": topic})
+    """
+    Generate content using the new CrewAI Flow-based approach
+    """
+    return generate_content_with_flow(topic)
 
 # Main content area
 if generate_button:

diff --git a/ai_news_generator/main.py b/ai_news_generator/main.py
@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""
+Main entry point for the AI News Generator using CrewAI Flows.
+
+This script provides a command-line interface to generate news content
+using the NewsGeneratorFlow implementation.
+"""
+
+import argparse
+import sys
+from typing import Optional
-from typing import Optional
-from typing import Optional
+from news_flow import NewsGeneratorFlow
+
+
+def main():
+    """
+    Main function to run the AI News Generator Flow from command line.
+    """
+    parser = argparse.ArgumentParser(
+        description="Generate AI news content using CrewAI Flows",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  python main.py --topic "Latest developments in artificial intelligence"
+  python main.py --topic "Climate change solutions" --output article.md
+        """
+    )
+
+    parser.add_argument(
+        "--topic",
+        type=str,
+        required=True,
+        help="Topic to research and write about"
+    )
+
+    parser.add_argument(
+        "--output",
+        type=str,
+        help="Output file to save the generated content (optional)"
+    )
+
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="Enable verbose logging"
+    )
+
+    args = parser.parse_args()
+
+    if not args.topic.strip():
+        print("Error: Topic cannot be empty", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        print(f"🚀 Starting AI News Generator Flow for topic: '{args.topic}'")
+        print("📊 Initializing research phase...")
+
+        # Create and run the flow
+        flow = NewsGeneratorFlow()
+        result = flow.kickoff(inputs={"topic": args.topic})
+
+        # Convert result to string if it's not already
+        content = str(result)
+
+        print("✅ Content generation completed!")
+
+        # Save to file if specified
+        if args.output:
+            try:
+                with open(args.output, 'w', encoding='utf-8') as f:
+                    f.write(content)
+                print(f"💾 Content saved to: {args.output}")
+            except IOError as e:
+                print(f"Error saving file: {e}", file=sys.stderr)
+                sys.exit(1)
+        else:
+            # Print to stdout
+            print("\n" + "="*80)
+            print("GENERATED CONTENT:")
+            print("="*80)
+            print(content)
+            print("="*80)
+
+        return 0
+
+    except KeyboardInterrupt:
+        print("\n⚠️ Operation cancelled by user", file=sys.stderr)
+        return 1
+    except Exception as e:
+        print(f"❌ Error: {e}", file=sys.stderr)
+        if args.verbose:
+            import traceback
+            traceback.print_exc()
+        return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())