Update app.py

app.py

@@ -17,6 +17,19 @@ CHAT_MODEL = "deepseek/deepseek-chat"
 TOP_K_CANDIDATES = 15
 TOP_N_SOURCES = 3
 
+# ============================================
+# GLOBAL STATE FOR DATA PASSING
+# ============================================
+class SessionState:
+    def __init__(self):
+        self.stage1_results = None
+        self.stage2_results = None
+        self.current_orphan_url = None
+        self.current_orphan_title = None
+        self.current_orphan_keyword = None
+
+session = SessionState()
+
 # ============================================
 # KNOWLEDGE BASE LOADER
 # ============================================
@@ -71,7 +84,7 @@ class KnowledgeBase:
         return results
 
 # ============================================
-# OPENROUTER CLIENT (FIXED)
+# OPENROUTER CLIENT
 # ============================================
 class OpenRouterClient:
     def __init__(self, api_key):
@@ -263,7 +276,7 @@ Link details:
 - Target page: {orphan_title}
 - Target URL: {orphan_url}
 
-Provide the modified sentence with the anchor text naturally integrated. Keep the modification minimal and natural. Provide ONLY the modified sentence."""
+Provide the modified sentence with the anchor text naturally integrated. Keep the modification minimal and natural. Provide ONLY the modified sentence, nothing else."""
 
             modified_text = self.client.chat([
                 {"role": "user", "content": prompt}
@@ -292,7 +305,7 @@ stage2 = None
 stage3 = None
 
 # ============================================
-# GRADIO INTERFACE
+# GRADIO INTERFACE FUNCTIONS
 # ============================================
 def setup_api_key(api_key):
     """Initialize OpenRouter client"""
@@ -328,28 +341,39 @@ def run_stage1(orphan_url, orphan_title, orphan_keyword, orphan_category):
         return "❌ Please provide at least URL and Title", None, None
     
     try:
+        # Store in session
+        session.current_orphan_url = orphan_url
+        session.current_orphan_title = orphan_title
+        session.current_orphan_keyword = orphan_keyword
+        
         all_candidates, top_3 = stage1.analyze(
             orphan_url, orphan_title, orphan_keyword, orphan_category
         )
         
+        # Store results
+        session.stage1_results = {
+            'all_candidates': all_candidates,
+            'top_3': top_3
+        }
+        
         # Format for display
         df_all = pd.DataFrame(all_candidates)[['url', 'title', 'score', 'similarity', 'opportunities']]
         df_top3 = pd.DataFrame(top_3)[['url', 'title', 'score']]
         
-        return "✅ Stage 1 complete!", df_all, df_top3
+        return "✅ Stage 1 complete! Proceed to Stage 2.", df_all, df_top3
     except Exception as e:
         return f"❌ Error: {str(e)}", None, None
 
 def run_stage2(orphan_url, orphan_title, orphan_keyword, selected_urls_text):
     """Run Stage 2 analysis"""
     if not stage2:
-        return "❌ Please configure your API key first!", None
+        return "❌ Please configure your API key first!", None, gr.update(visible=False)
     
     # Parse selected URLs
     selected_urls = [url.strip() for url in selected_urls_text.split('\n') if url.strip()]
     
     if len(selected_urls) != 3:
-        return f"❌ Please provide exactly 3 URLs (you provided {len(selected_urls)})", None
+        return f"❌ Please provide exactly 3 URLs (you provided {len(selected_urls)})", None, gr.update(visible=False)
     
     # Get source details from KB
     selected_sources = []
@@ -362,11 +386,19 @@ def run_stage2(orphan_url, orphan_title, orphan_keyword, selected_urls_text):
             })
     
     if len(selected_sources) != 3:
-        return f"❌ Some URLs not found in knowledge base", None
+        return f"❌ Some URLs not found in knowledge base", None, gr.update(visible=False)
     
     try:
+        # Update session
+        session.current_orphan_url = orphan_url
+        session.current_orphan_title = orphan_title
+        session.current_orphan_keyword = orphan_keyword
+        
         placements = stage2.analyze(orphan_url, orphan_title, orphan_keyword, selected_sources)
         
+        # Store in session for Stage 3
+        session.stage2_results = placements
+        
         # Format for display
         df = pd.DataFrame([{
             'Source URL': p['source_url'],
@@ -377,14 +409,99 @@ def run_stage2(orphan_url, orphan_title, orphan_keyword, selected_urls_text):
             'Current Text (preview)': p['current_text'][:100] + '...'
         } for p in placements])
         
-        return "✅ Stage 2 complete!", df
+        return "✅ Stage 2 complete! Click 'Stage 3' tab to generate implementation report.", df, gr.update(visible=True)
+    except Exception as e:
+        return f"❌ Error: {str(e)}", None, gr.update(visible=False)
+
+def run_stage3():
+    """Run Stage 3 report generation - automatically uses data from Stage 2"""
+    if not stage3:
+        return "❌ Please configure your API key first!", "", None, ""
+    
+    if not session.stage2_results:
+        return "❌ Please complete Stage 2 first!", "", None, ""
+    
+    try:
+        # Generate implementations using stored data
+        implementations = stage3.generate(
+            session.current_orphan_url,
+            session.current_orphan_title,
+            session.stage2_results
+        )
+        
+        # Format summary
+        avg_score = sum(p['score'] for p in implementations) // len(implementations)
+        summary_md = f"""
+### 📊 Implementation Summary
+
+**Orphan Page:** {session.current_orphan_title}  
+**Target URL:** {session.current_orphan_url}
+
+**Statistics:**
+- ✅ Total links to implement: **{len(implementations)}**
+- 📈 Average placement score: **{avg_score}/100**
+- 🎯 Anchor text diversity: **Excellent** (all unique)
+- 🔗 Total backlinks created: **{len(implementations)} unique inbound links**
+
+**Next Steps:**
+1. Review the implementation table below
+2. Copy the HTML code snippets
+3. Navigate to each source page in Webflow
+4. Replace the current text with the HTML code
+5. Publish changes
+        """
+        
+        # Format table
+        df = pd.DataFrame([{
+            'Source Page': impl['source_title'][:40],
+            'Para #': impl['paragraph_index'],
+            'Anchor Text': impl['anchor_text'],
+            'Score': impl['score'],
+            'Current Text (first 80 chars)': impl['current_text'][:80] + '...',
+            'Modified Text (first 80 chars)': impl['modified_text'][:80] + '...'
+        } for impl in implementations])
+        
+        # Format HTML output with detailed instructions
+        html_sections = []
+        for i, impl in enumerate(implementations):
+            html_sections.append(f"""
+{'='*80}
+LINK {i+1} of {len(implementations)}
+{'='*80}
+
+SOURCE PAGE: {impl['source_title']}
+URL: {impl['source_url']}
+PARAGRAPH #: {impl['paragraph_index']}
+PLACEMENT SCORE: {impl['score']}/100
+
+---
+CURRENT TEXT (FIND THIS IN WEBFLOW):
+---
+{impl['current_text'][:300]}...
+
+---
+REPLACE WITH THIS HTML CODE:
+---
+{impl['html_code']}
+
+---
+ANCHOR TEXT: "{impl['anchor_text']}"
+TARGET URL: {session.current_orphan_url}
+---
+
+""")
+        
+        html_output = "\n".join(html_sections)
+        
+        return "✅ Stage 3 complete! Review and implement the suggestions below.", summary_md, df, html_output
+        
     except Exception as e:
-        return f"❌ Error: {str(e)}", None
+        return f"❌ Error: {str(e)}", "", None, ""
 
 # ============================================
 # BUILD INTERFACE
 # ============================================
-with gr.Blocks(title="Edstellar Internal Linking Tool") as app:
+with gr.Blocks(title="Edstellar Internal Linking Tool", theme=gr.themes.Soft()) as app:
     gr.Markdown("# 🔗 Edstellar Internal Linking RAG Tool")
     gr.Markdown("AI-powered 3-stage analysis to find optimal internal linking opportunities for orphan pages")
     
@@ -397,12 +514,13 @@ with gr.Blocks(title="Edstellar Internal Linking Tool") as app:
                 placeholder="sk-or-v1-...",
                 type="password"
             )
-            api_setup_btn = gr.Button("Configure API Key")
+            api_setup_btn = gr.Button("Configure API Key", variant="primary")
         
         api_status = gr.Textbox(label="Status", interactive=False)
         
         gr.Markdown("---")
         gr.Markdown("## Step 2: Load Knowledge Base")
+        gr.Markdown("*This loads your pre-built knowledge base with 523 searchable blog paragraphs*")
         
         with gr.Row():
             hf_token_input = gr.Textbox(
@@ -410,68 +528,153 @@ with gr.Blocks(title="Edstellar Internal Linking Tool") as app:
                 placeholder="hf_...",
                 type="password"
             )
-            kb_load_btn = gr.Button("Load Knowledge Base")
+            kb_load_btn = gr.Button("Load Knowledge Base", variant="primary")
         
         kb_status = gr.Textbox(label="Status", interactive=False)
     
     with gr.Tab("📊 Stage 1: Find Source Pages"):
         gr.Markdown("## Identify Top 15 Candidates → Select Best 3")
+        gr.Markdown("Enter your orphan page details to find the best source pages for internal links")
         
         with gr.Row():
             with gr.Column():
-                s1_orphan_url = gr.Textbox(label="Orphan Page URL", placeholder="https://edstellar.com/blog/...")
-                s1_orphan_title = gr.Textbox(label="Orphan Page Title", placeholder="Employee Training Tips")
-                s1_orphan_keyword = gr.Textbox(label="Primary Keyword", placeholder="employee training")
-                s1_orphan_category = gr.Textbox(label="Category", placeholder="Learning & Development")
-                s1_analyze_btn = gr.Button("🔍 Find Source Pages", variant="primary")
+                s1_orphan_url = gr.Textbox(
+                    label="Orphan Page URL",
+                    placeholder="https://edstellar.com/blog/employee-training-tips"
+                )
+                s1_orphan_title = gr.Textbox(
+                    label="Orphan Page Title",
+                    placeholder="Employee Training Tips"
+                )
+                s1_orphan_keyword = gr.Textbox(
+                    label="Primary Keyword",
+                    placeholder="employee training"
+                )
+                s1_orphan_category = gr.Textbox(
+                    label="Category",
+                    placeholder="Learning & Development"
+                )
+                s1_analyze_btn = gr.Button("🔍 Find Source Pages", variant="primary", size="lg")
             
             with gr.Column():
-                s1_status = gr.Textbox(label="Status")
+                s1_status = gr.Textbox(label="Status", lines=3)
         
         gr.Markdown("### 📋 All Candidates (Top 15)")
-        s1_all_candidates = gr.Dataframe(label="All Candidates", interactive=False)
+        s1_all_candidates = gr.Dataframe(
+            label="All Candidates",
+            interactive=False,
+            wrap=True
+        )
         
         gr.Markdown("### ⭐ Recommended Top 3")
-        s1_top3 = gr.Dataframe(label="Top 3 Sources", interactive=False)
+        gr.Markdown("*These are automatically selected based on relevance, category match, and linking potential*")
+        s1_top3 = gr.Dataframe(
+            label="Top 3 Sources",
+            interactive=False
+        )
     
     with gr.Tab("📍 Stage 2: Find Placements"):
         gr.Markdown("## Identify Exact Link Placement Locations")
+        gr.Markdown("Paste 3 source URLs (from Stage 1) to find optimal paragraph placements")
         
         with gr.Row():
             with gr.Column():
-                s2_orphan_url = gr.Textbox(label="Orphan Page URL")
-                s2_orphan_title = gr.Textbox(label="Orphan Page Title")
-                s2_orphan_keyword = gr.Textbox(label="Primary Keyword")
+                s2_orphan_url = gr.Textbox(
+                    label="Orphan Page URL",
+                    placeholder="(Copy from Stage 1)"
+                )
+                s2_orphan_title = gr.Textbox(
+                    label="Orphan Page Title",
+                    placeholder="(Copy from Stage 1)"
+                )
+                s2_orphan_keyword = gr.Textbox(
+                    label="Primary Keyword",
+                    placeholder="(Copy from Stage 1)"
+                )
                 s2_selected_urls = gr.Textbox(
                     label="Selected 3 URLs (one per line)",
                     placeholder="https://edstellar.com/blog/page1\nhttps://edstellar.com/blog/page2\nhttps://edstellar.com/blog/page3",
                     lines=4
                 )
-                s2_analyze_btn = gr.Button("🎯 Find Placements", variant="primary")
+                s2_analyze_btn = gr.Button("🎯 Find Placements", variant="primary", size="lg")
             
             with gr.Column():
-                s2_status = gr.Textbox(label="Status")
+                s2_status = gr.Textbox(label="Status", lines=5)
+        
+        s2_placements = gr.Dataframe(
+            label="Placement Recommendations",
+            interactive=False,
+            wrap=True
+        )
         
-        s2_placements = gr.Dataframe(label="Placement Recommendations", interactive=False)
+        s2_proceed_notice = gr.Markdown(
+            "✅ **Data saved!** Click the **Stage 3** tab to generate implementation report.",
+            visible=False
+        )
     
     with gr.Tab("📄 Stage 3: Implementation Report"):
         gr.Markdown("## Generate Ready-to-Use HTML Code")
-        gr.Markdown("*Coming soon: Full implementation report with copy-paste HTML*")
+        gr.Markdown("Automatically generates implementation guide using results from Stage 2")
+        
+        gr.Markdown("### ⚡ Quick Start")
+        gr.Markdown("Click the button below to generate your implementation report. No manual input needed!")
+        
+        s3_generate_btn = gr.Button(
+            "📋 Generate Implementation Report",
+            variant="primary",
+            size="lg"
+        )
+        
+        s3_status = gr.Textbox(label="Status", lines=2)
+        
+        s3_summary = gr.Markdown()
+        
+        gr.Markdown("### 📊 Implementation Table")
+        s3_report = gr.Dataframe(
+            label="Detailed Recommendations",
+            interactive=False,
+            wrap=True
+        )
+        
+        gr.Markdown("### 💻 HTML Code Snippets")
+        gr.Markdown("Copy each section and paste into the corresponding Webflow page")
+        s3_html_output = gr.Code(
+            label="Copy-Paste Ready Implementation Guide",
+            language="html",
+            lines=20
+        )
     
     # Wire up events
-    api_setup_btn.click(setup_api_key, inputs=[api_key_input], outputs=[api_status])
-    kb_load_btn.click(load_kb, inputs=[hf_token_input], outputs=[kb_status])
+    api_setup_btn.click(
+        setup_api_key,
+        inputs=[api_key_input],
+        outputs=[api_status]
+    )
+    
+    kb_load_btn.click(
+        load_kb,
+        inputs=[hf_token_input],
+        outputs=[kb_status]
+    )
+    
     s1_analyze_btn.click(
         run_stage1,
         inputs=[s1_orphan_url, s1_orphan_title, s1_orphan_keyword, s1_orphan_category],
         outputs=[s1_status, s1_all_candidates, s1_top3]
     )
+    
     s2_analyze_btn.click(
         run_stage2,
         inputs=[s2_orphan_url, s2_orphan_title, s2_orphan_keyword, s2_selected_urls],
-        outputs=[s2_status, s2_placements]
+        outputs=[s2_status, s2_placements, s2_proceed_notice]
+    )
+    
+    s3_generate_btn.click(
+        run_stage3,
+        inputs=[],  # No inputs needed - uses session data
+        outputs=[s3_status, s3_summary, s3_report, s3_html_output]
     )
 
 # Launch
 if __name__ == "__main__":
-    app.launch()
+    app.launch()