Add application files

GRADIO_5_FIX.md

@@ -0,0 +1,152 @@
+# Gradio 5.x Message Format Fix
+
+## Issue
+```
+gradio.exceptions.Error: "Data incompatible with messages format. Each message should be a dictionary with 'role' and 'content' keys or a ChatMessage object."
+```
+
+## Root Cause
+Gradio 5.x changed the chatbot message format from tuples to dictionaries.
+
+### Old Format (Gradio 4.x):
+```python
+chat_history.append((None, "Assistant message"))
+chat_history.append(("User message", "Assistant response"))
+```
+
+### New Format (Gradio 5.x):
+```python
+chat_history.append({"role": "assistant", "content": "Assistant message"})
+chat_history.append({"role": "user", "content": "User message"})
+chat_history.append({"role": "assistant", "content": "Assistant response"})
+```
+
+## Fixed Files
+- `app.py` - Updated all message additions to use dictionary format
+
+## Changes Made
+
+### 1. Initial Message
+**Before:**
+```python
+chat_history.append((None, "Starting pipeline..."))
+```
+
+**After:**
+```python
+chat_history.append({
+    "role": "assistant",
+    "content": "Starting pipeline..."
+})
+```
+
+### 2. Company Processing Messages
+**Before:**
+```python
+chat_history.append((
+    f"Process {company}",
+    f"Processing: {company}"
+))
+```
+
+**After:**
+```python
+chat_history.append({
+    "role": "assistant",
+    "content": f"Processing: {company}",
+    "metadata": {"company": company}  # For tracking updates
+})
+```
+
+### 3. Updating Streaming Messages
+**Before:**
+```python
+if chat_history and chat_history[-1][0] == f"Process {company}":
+    chat_history[-1] = (f"Process {company}", updated_content)
+```
+
+**After:**
+```python
+if chat_history and chat_history[-1].get("metadata", {}).get("company") == company:
+    chat_history[-1]["content"] = updated_content
+```
+
+### 4. Error/Status Messages
+**Before:**
+```python
+chat_history.append((None, "Error occurred"))
+```
+
+**After:**
+```python
+chat_history.append({
+    "role": "assistant",
+    "content": "Error occurred"
+})
+```
+
+## Message Roles
+
+Gradio 5.x supports these roles:
+- `"user"` - User messages
+- `"assistant"` - Assistant/bot messages
+- `"system"` - System messages (optional)
+
+For this application, all messages are from the assistant role since it's a pipeline monitoring interface.
+
+## Testing
+
+After the fix, test with:
+```bash
+python app.py
+# Enter a company name and run the pipeline
+```
+
+Expected: Messages should display properly without format errors.
+
+## Chatbot Configuration
+
+The chatbot component is configured as:
+```python
+gr.Chatbot(
+    label="Agent Output & Generated Content",
+    height=600,
+    type="messages"  # This enables the new format
+)
+```
+
+## Additional Notes
+
+### Metadata Field
+We added a `metadata` field to track which company each message belongs to:
+```python
+{
+    "role": "assistant",
+    "content": "...",
+    "metadata": {"company": "Shopify"}
+}
+```
+
+This allows us to update the correct message when streaming tokens for a specific company.
+
+### Streaming Updates
+For real-time token streaming, we update the message in place:
+```python
+# Find the message for this company
+if chat_history[-1].get("metadata", {}).get("company") == company:
+    # Update its content
+    chat_history[-1]["content"] = new_content
+```
+
+## Migration Checklist
+
+If you have other Gradio interfaces, check for:
+- [ ] All `chat_history.append()` use dictionary format
+- [ ] Chatbot component has `type="messages"`
+- [ ] Message updates modify the `"content"` key, not tuple indices
+- [ ] All roles are valid: "user", "assistant", or "system"
+
+## Resources
+
+- [Gradio 5.0 Migration Guide](https://www.gradio.app/guides/migration-guide-5)
+- [Chatbot Component Docs](https://www.gradio.app/docs/chatbot)

app.py

@@ -63,12 +63,15 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
         # Fallback to example companies
         company_names = ["Shopify", "Stripe"]
 
-    # Chat history for display
+    # Chat history for display (Gradio 5.x format)
     chat_history = []
     workflow_logs = []
 
     # Start pipeline message
-    chat_history.append((None, f"🚀 **Starting Dynamic CX Agent Pipeline...**\n\nDiscovering and processing {len(company_names)} companies:\n- " + "\n- ".join(company_names) + "\n\nUsing web search to find live data..."))
+    chat_history.append({
+        "role": "assistant",
+        "content": f"🚀 **Starting Dynamic CX Agent Pipeline...**\n\nDiscovering and processing {len(company_names)} companies:\n- " + "\n- ".join(company_names) + "\n\nUsing web search to find live data..."
+    })
     yield chat_history, "Initializing pipeline...", format_workflow_logs(workflow_logs)
 
     try:
@@ -133,10 +136,11 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
                 })
 
                 # Add company section to chat
-                chat_history.append((
-                    f"Process {company}",
-                    f"🏢 **{company}**\n\n*Industry:* {industry}\n*Size:* {size} employees\n\nGenerating personalized content..."
-                ))
+                chat_history.append({
+                    "role": "assistant",
+                    "content": f"🏢 **{company}**\n\n*Industry:* {industry}\n*Size:* {size} employees\n\nGenerating personalized content...",
+                    "metadata": {"company": company}  # Track which company this is
+                })
                 status = f"🏢 Processing {company}"
 
             elif event_type == "llm_token":
@@ -164,9 +168,9 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
                 if email:
                     content += f"**✉️ Email Draft:**\n{email}"
 
-                # Update last message
-                if chat_history and chat_history[-1][0] == f"Process {company}":
-                    chat_history[-1] = (f"Process {company}", content)
+                # Update last message if it's for this company
+                if chat_history and chat_history[-1].get("metadata", {}).get("company") == company:
+                    chat_history[-1]["content"] = content
 
                 status = f"✍️ Writing content for {company}..."
 
@@ -185,8 +189,8 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
                     content += str(email)
 
                 # Update last message with final content
-                if chat_history and chat_history[-1][0] == f"Process {company}":
-                    chat_history[-1] = (f"Process {company}", content)
+                if chat_history and chat_history[-1].get("metadata", {}).get("company") == company:
+                    chat_history[-1]["content"] = content
 
                 workflow_logs.append({
                     "time": timestamp,
@@ -204,7 +208,10 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
                     "action": "❌ Blocked",
                     "details": reason
                 })
-                chat_history.append((None, f"❌ **Compliance Block**: {reason}"))
+                chat_history.append({
+                    "role": "assistant",
+                    "content": f"❌ **Compliance Block**: {reason}"
+                })
                 status = f"❌ Blocked: {reason}"
 
             elif event_type == "policy_pass":
@@ -231,12 +238,18 @@ async def run_pipeline_gradio(company_names_input: str) -> AsyncGenerator[tuple,
 
 All prospects have been enriched, scored, and prepared for outreach through the autonomous agent system.
 """
-        chat_history.append((None, final_msg))
+        chat_history.append({
+            "role": "assistant",
+            "content": final_msg
+        })
         yield chat_history, "✅ Pipeline Complete", format_workflow_logs(workflow_logs)
 
     except Exception as e:
         error_msg = f"❌ **Pipeline Error:** {str(e)}"
-        chat_history.append((None, error_msg))
+        chat_history.append({
+            "role": "assistant",
+            "content": error_msg
+        })
         yield chat_history, f"Error: {str(e)}", format_workflow_logs(workflow_logs)
 
     finally: