Update app.py

app.py

@@ -3,20 +3,16 @@ from swarm import Swarm, Agent
 from bs4 import BeautifulSoup
 import requests
 import os
-import json
-from io import BytesIO
-from reportlab.lib.pagesizes import letter
-from reportlab.pdfgen import canvas
 
 # Function to fetch OpenAI API key
 def fetch_openai_api_key():
-    """Fetch the OpenAI API key from Streamlit secrets."""
+    """Fetch the OpenAI API key from Hugging Face secrets."""
     try:
         secret_key = st.secrets.get("OPENAI_API_KEY", "")
         if secret_key:
             os.environ['OPENAI_API_KEY'] = secret_key
         else:
-            st.warning("⚠️ OpenAI API Key is missing! Please check your secrets configuration.")
+            st.warning("⚠️ OpenAI API Key is missing! Please check your Hugging Face secrets configuration.")
     except Exception as e:
         st.error(f"Error retrieving OpenAI API Key: {str(e)}")
 
@@ -31,60 +27,73 @@ def scrape_website(url):
         response = requests.get(url)
         response.raise_for_status()
         soup = BeautifulSoup(response.text, 'html.parser')
-
-        # Extract metadata
-        metadata = {
-            "title": soup.title.string if soup.title else "N/A",
-            "description": soup.find("meta", {"name": "description"})["content"] if soup.find("meta", {"name": "description"}) else "N/A",
-            "keywords": soup.find("meta", {"name": "keywords"})["content"] if soup.find("meta", {"name": "keywords"}) else "N/A",
-        }
-
-        text_content = soup.get_text()  # Extract text content
-        return {"text": text_content, "metadata": metadata}
+        return soup.get_text()  # Return the text content from the HTML
     except requests.exceptions.RequestException as e:
         return f"Error during scraping: {str(e)}"
 
-# Enhanced summarization function
+# Scraper Agent
+scraper_agent = Agent(
+    name="Scraper Agent",
+    instructions="You are an agent that scrapes content from websites.",
+    functions=[scrape_website]
+)
+
+# Define the analysis function
 def analyze_content(content):
     """Analyzes the scraped content for key points."""
-    summary = f"Summary of content: {content[:500]}..."  
+    summary = f"Summary of content: {content[:200]}..."  # A simple placeholder summarization
     return summary
 
+# Research Agent
+research_agent = Agent(
+    name="Research Agent",
+    instructions="You are an agent that analyzes content and extracts key insights.",
+    functions=[analyze_content]
+)
+
 # Define the writing function
 def write_summary(context_variables):
     """Writes a summary based on the analysis."""
     analysis = context_variables.get('analysis', '')
-    metadata = context_variables.get('metadata', {})
-
-    detailed_report = (
-        f"### Metadata:\n"
-        f"**Title:** {metadata.get('title')}\n"
-        f"**Description:** {metadata.get('description')}\n"
-        f"**Keywords:** {metadata.get('keywords')}\n\n"
-        f"### Content Summary:\n{analysis}"
+    summary = f"Here's a detailed report based on the research: {analysis}"
+    return summary
+
+# Writer Agent
+writer_agent = Agent(
+    name="Writer Agent",
+    instructions="You are an agent that writes summaries of research.",
+    functions=[write_summary]
+)
+
+# Orchestrate the workflow
+def orchestrate_workflow(client, url):
+    # Step 1: Scrape the website
+    scrape_result = client.run(
+        agent=scraper_agent,
+        messages=[{"role": "user", "content": f"Scrape the following website: {url}"}]
     )
-    return detailed_report
-
-# Generate PDF report
-def generate_pdf(report):
-    """Generate a PDF file from the report."""
-    buffer = BytesIO()
-    pdf_canvas = canvas.Canvas(buffer, pagesize=letter)
-    pdf_canvas.drawString(100, 750, "Web Content Analyzer Report")
-    pdf_canvas.drawString(100, 735, "-" * 50)
-    
-    lines = report.split('\n')
-    y = 700  # Start position for the text
-    for line in lines:
-        if y < 50:  # Create a new page if content exceeds one page
-            pdf_canvas.showPage()
-            y = 750
-        pdf_canvas.drawString(100, y, line)
-        y -= 15
-    
-    pdf_canvas.save()
-    buffer.seek(0)
-    return buffer
+    scraped_content = scrape_result.messages[-1]["content"]
+
+    # Check for any error during scraping
+    if "Error during scraping" in scraped_content:
+        return scraped_content
+
+    # Step 2: Analyze the scraped content
+    research_result = client.run(
+        agent=research_agent,
+        messages=[{"role": "user", "content": f"Analyze the following content: {scraped_content}"}]
+    )
+    analysis_summary = research_result.messages[-1]["content"]
+
+    # Step 3: Write the summary based on the analysis
+    writer_result = client.run(
+        agent=writer_agent,
+        messages=[{"role": "user", "content": f"Write a summary based on this analysis: {analysis_summary}"}],
+        context_variables={"analysis": analysis_summary}
+    )
+
+    final_summary = writer_result.messages[-1]["content"]
+    return final_summary
 
 # Streamlit App UI
 st.markdown(
@@ -99,11 +108,15 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
-st.markdown('<div class="title">🔎 Multi-Agent Web Content Analyzer</div>', unsafe_allow_html=True)
-st.markdown('<div class="description">Extract, analyze, and summarize web content with advanced capabilities.</div>', unsafe_allow_html=True)
+st.markdown('<div class="title">🔎 Swarm-based Web Content Analyzer</div>', unsafe_allow_html=True)
+st.markdown('<div class="description">Effortlessly extract, analyze, and summarize web content.</div>', unsafe_allow_html=True)
+
+st.write("")
+st.write("")
 
 fetch_openai_api_key()
 
+# Initialize Swarm client only after API key is set
 if 'OPENAI_API_KEY' in os.environ and os.environ['OPENAI_API_KEY']:
     client = initialize_swarm_client()
 
@@ -112,55 +125,20 @@ if 'OPENAI_API_KEY' in os.environ and os.environ['OPENAI_API_KEY']:
     url = st.text_input("Enter the URL of the website you want to scrape", placeholder="https://example.com")
 
     # Run Workflow button
+    st.write("")
+
     if st.button("Run Workflow"):
         if url:
             with st.spinner("Running the multi-agent workflow... This may take a moment."):
-                scrape_result = scrape_website(url)
-                if isinstance(scrape_result, str):  # Error handling
-                    st.error(scrape_result)
-                else:
-                    content = scrape_result["text"]
-                    metadata = scrape_result["metadata"]
-
-                    # Analysis and writing
-                    analysis_summary = analyze_content(content)
-                    final_summary = write_summary({
-                        "analysis": analysis_summary,
-                        "metadata": metadata,
-                    })
-
-                    st.success("✅ Workflow complete!")
-                    st.write("### 📜 Final Report:")
-                    st.markdown(final_summary, unsafe_allow_html=True)
-
-                    # Prepare downloadable content
-                    report_file_json = json.dumps({
-                        "metadata": metadata,
-                        "summary": analysis_summary
-                    }, indent=4)
-                    report_file_txt = final_summary
-                    report_file_pdf = generate_pdf(final_summary)
-
-                    # Download options
-                    st.download_button(
-                        label="Download Report as JSON",
-                        data=report_file_json,
-                        file_name="report.json",
-                        mime="application/json"
-                    )
-                    st.download_button(
-                        label="Download Report as TXT",
-                        data=report_file_txt,
-                        file_name="report.txt",
-                        mime="text/plain"
-                    )
-                    st.download_button(
-                        label="Download Report as PDF",
-                        data=report_file_pdf,
-                        file_name="report.pdf",
-                        mime="application/pdf"
-                    )
+                final_report = orchestrate_workflow(client, url)
+            st.success("✅ Workflow complete!")
+            st.write("### 📜 Final Report:")
+            st.write(final_report)
         else:
             st.error("❌ Please enter a valid URL.")
 else:
-    st.sidebar.warning("⚠️ OpenAI API Key not set. Please check your secrets configuration.")
+    st.sidebar.warning("⚠️ OpenAI API Key not set. Please check your Hugging Face secrets configuration.")
+
+# Footer with credits
+st.divider()
+st.markdown('<div class="ack">Acknowledgement: </div>', unsafe_allow_html=True)