Add ModerationAgent and update QualityScoringAgent accordingly

packages.txt

@@ -0,0 +1 @@
+ffmpeg

src/agents/ModerationAgent.py

@@ -0,0 +1,31 @@
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import PromptTemplate
+from src.agents.CallState import CallState
+
+class ModerationAgent:
+    """
+    Agent that uses LLM to detect and redact obscene words, replacing them with ***.
+    Updates the clean_content in the state.
+    """
+
+    def __init__(self):
+        self.llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+
+    def __call__(self, state: CallState) -> CallState:
+        text = state.get("clean_content") or state.get("content") or ""
+        if not text:
+            return state
+
+        prompt = PromptTemplate.from_template(
+            "You are a moderation assistant. Review the following text. "
+            "If you find any obscene words, profanity, or inappropriate language, replace them entirely with ***. "
+            "Do not change any other words. Return only the redacted text.\n\n"
+            "Text:\n{text}"
+        )
+        
+        chain = prompt | self.llm
+        result = chain.invoke({"text": text})
+        
+        # Save the redacted text back to clean_content
+        state["clean_content"] = result.content
+        return state

src/agents/QualityScoringAgent.py

@@ -25,6 +25,13 @@ class QualityScoringAgent:
         
         try:
             result_json = json.loads(result_text)
+            profanity_count = clean_text.count("***")
+            if profanity_count > 0:
+                result_json["profanity"] = profanity_count
+                for key in ["tone", "professionalism", "structured_resolution"]:
+                    if key in result_json and isinstance(result_json[key], (int, float)):
+                        result_json[key] = max(0, result_json[key] - 3)
+                        
             state["quality_scores"] = result_json
         except json.JSONDecodeError:
             state["quality_scores"] = {"raw_evaluation": result_text}

src/agents/__init__.py

@@ -3,4 +3,5 @@ from .IntakeAgent import IntakeAgent
 from .TranscriptionAgent import TranscriptionAgent
 from .SummarizationAgent import SummarizationAgent
 from .QualityScoringAgent import QualityScoringAgent
+from .ModerationAgent import ModerationAgent
 from .Router import Router

src/streamlit_app.py

@@ -12,17 +12,18 @@ sys.path.append(os.path.dirname(os.path.dirname(__file__)))
 
 PROCESSED_DIR = "data/processed_results"
 
+
 def apply_material_css():
     st.markdown("""
         <style>
         /* Material Design CSS Overrides */
-        
+
         .stApp {
             font-family: 'Roboto', 'Inter', sans-serif;
             background-color: #121212;
             color: #FFFFFF;
         }
-        
+
         /* Material Cards for metrics and sections */
         .material-card {
             background-color: #1E1E1E;
@@ -31,11 +32,11 @@ def apply_material_css():
             box-shadow: 0 4px 6px rgba(0,0,0,0.3);
             margin-bottom: 20px;
         }
-        
+
         h1, h2, h3, h4 {
             font-weight: 500;
         }
-        
+
         /* Subtle styling for Streamlit columns to look like cards */
         [data-testid="column"] {
             background-color: #1E1E1E;
@@ -43,18 +44,19 @@ def apply_material_css():
             padding: 20px;
             box-shadow: 0 4px 6px rgba(0,0,0,0.3);
         }
-        
+
         </style>
     """, unsafe_allow_html=True)
 
+
 def display_results(final_state):
     st.subheader("Workflow Results")
-    
+
     col1, col2 = st.columns(2)
     with col1:
         st.markdown("### Summary")
         st.write(final_state.get("summary", "No summary generated."))
-        
+
         st.markdown("### Key Points")
         key_points = final_state.get("key_points", "No key points generated.")
         if isinstance(key_points, list):
@@ -62,7 +64,7 @@ def display_results(final_state):
                 st.markdown(f"- {point}")
         else:
             st.write(key_points)
-        
+
     with col2:
         st.markdown("### Quality Scores")
         quality_scores = final_state.get("quality_scores", {})
@@ -90,7 +92,7 @@ def display_results(final_state):
                         ))
                         # Adjust colors for dark theme
                         fig.update_layout(
-                            height=180, 
+                            height=180,
                             margin=dict(l=20, r=20, t=40, b=20),
                             paper_bgcolor='#1E1E1E',
                             plot_bgcolor='#1E1E1E',
@@ -99,12 +101,12 @@ def display_results(final_state):
                         st.plotly_chart(fig, use_container_width=True)
                     except (ValueError, TypeError):
                         st.write(f"**{metric.replace('_', ' ').title()}**: {quality_scores[metric]}")
-            
+
             if "notes" in quality_scores:
                 st.write("**Notes:**", quality_scores["notes"])
         else:
             st.write("No specific scores generated.", quality_scores)
-        
+
         st.markdown("### Metadata")
         metadata = final_state.get("metadata", {})
         if isinstance(metadata, dict) and metadata:
@@ -113,15 +115,16 @@ def display_results(final_state):
         else:
             st.write("No metadata available.")
 
+
 def main():
     st.set_page_config(page_title="Call Center Data Analysis", layout="wide")
     apply_material_css()
-    
+
     st.title("Call Center Data Analysis Dashboard")
-    
+
     os.makedirs(PROCESSED_DIR, exist_ok=True)
     os.makedirs("tmp", exist_ok=True)
-    
+
     if "view_mode" not in st.session_state:
         st.session_state.view_mode = "none"
 
@@ -133,22 +136,27 @@ def main():
 
     st.sidebar.header("Upload New File")
     uploaded_file = st.sidebar.file_uploader(
-        "Upload a file", 
+        "Upload a file",
         type=["json", "mp3", "wav", "csv"],
         on_change=set_upload_mode
     )
-    
+
     st.sidebar.markdown("---")
     st.sidebar.header("Processed Files")
-    
+
     # Get list of processed files
     processed_files = [f for f in os.listdir(PROCESSED_DIR) if f.endswith(".json")]
-    processed_files.sort(reverse=True) # Show newest (or reverse alphabetical) first
-    
+    processed_files.sort(reverse=True)  # Show newest (or reverse alphabetical) first
+
     selected_file = None
     if processed_files:
         options = ["-- Select a file --"] + processed_files
-        selected_dropdown = st.sidebar.selectbox("View cached results:", options, on_change=set_dropdown_mode)
+        selected_dropdown = st.sidebar.selectbox(
+            "View cached results:",
+            options,
+            format_func=lambda x: x.replace(".json", "") if x != "-- Select a file --" else x,
+            on_change=set_dropdown_mode
+        )
         if selected_dropdown != "-- Select a file --":
             selected_file = selected_dropdown
     else:
@@ -157,18 +165,18 @@ def main():
     # Prioritize based on view_mode
     if st.session_state.view_mode == "upload" and uploaded_file is not None:
         st.success(f"File '{uploaded_file.name}' uploaded successfully!")
-        
+
         from src.workflow import build_workflow
-        
+
         file_path = os.path.join("tmp", uploaded_file.name)
         with open(file_path, "wb") as f:
             f.write(uploaded_file.getbuffer())
-        
+
         file_extension = uploaded_file.name.split('.')[-1].lower()
-        
+
         # Check if already processed to avoid reprocessing on rerun if same file is in uploader
         cached_json_path = os.path.join(PROCESSED_DIR, f"{uploaded_file.name}.json")
-        
+
         if os.path.exists(cached_json_path):
             st.info("Loading cached results for this file...")
             with open(cached_json_path, 'r') as f:
@@ -182,35 +190,38 @@ def main():
                     "file_path": file_path,
                     "file_type": file_extension
                 }
-                
+
                 final_state = workflow.invoke(initial_state)
-                
+
                 # Cache the results
                 with open(cached_json_path, 'w') as f:
                     json.dump(final_state, f)
-                    
+
+                st.rerun()
+
             display_results(final_state)
-            
-    elif (st.session_state.view_mode == "dropdown" or st.session_state.view_mode == "none") and selected_file is not None:
+
+    elif (
+            st.session_state.view_mode == "dropdown" or st.session_state.view_mode == "none") and selected_file is not None:
         st.info(f"Loading cached results for '{selected_file.replace('.json', '')}'")
         cached_json_path = os.path.join(PROCESSED_DIR, selected_file)
         with open(cached_json_path, 'r') as f:
             final_state = json.load(f)
         display_results(final_state)
-        
-    elif uploaded_file is not None:
+
+    elif st.session_state.view_mode != "dropdown" and uploaded_file is not None:
         st.success(f"File '{uploaded_file.name}' uploaded successfully!")
-        
+
         from src.workflow import build_workflow
-        
+
         file_path = os.path.join("tmp", uploaded_file.name)
         with open(file_path, "wb") as f:
             f.write(uploaded_file.getbuffer())
-        
+
         file_extension = uploaded_file.name.split('.')[-1].lower()
-        
+
         cached_json_path = os.path.join(PROCESSED_DIR, f"{uploaded_file.name}.json")
-        
+
         if os.path.exists(cached_json_path):
             st.info("Loading cached results for this file...")
             with open(cached_json_path, 'r') as f:
@@ -227,11 +238,12 @@ def main():
                 final_state = workflow.invoke(initial_state)
                 with open(cached_json_path, 'w') as f:
                     json.dump(final_state, f)
+                st.rerun()
             display_results(final_state)
-        
+
     else:
         st.info("Please upload a file or select a previously processed file.")
 
+
 if __name__ == "__main__":
     main()
-

src/workflow.py

@@ -5,6 +5,7 @@ from src.agents import (
     TranscriptionAgent,
     SummarizationAgent,
     QualityScoringAgent,
+    ModerationAgent,
     Router
 )
 
@@ -14,6 +15,7 @@ def build_workflow():
     # Initialize agents
     intake_agent = IntakeAgent()
     transcription_agent = TranscriptionAgent()
+    moderation_agent = ModerationAgent()
     summarization_agent = SummarizationAgent()
     quality_scoring_agent = QualityScoringAgent()
     router = Router()
@@ -21,6 +23,7 @@ def build_workflow():
     # Add nodes
     workflow.add_node("intake", intake_agent)
     workflow.add_node("transcribe", transcription_agent)
+    workflow.add_node("moderate", moderation_agent)
     workflow.add_node("summarize", summarization_agent)
     workflow.add_node("score", quality_scoring_agent)
     
@@ -33,12 +36,13 @@ def build_workflow():
         router,
         {
             "transcribe": "transcribe",
-            "summarize": "summarize"
+            "summarize": "moderate"
         }
     )
     
     # Add standard edges
-    workflow.add_edge("transcribe", "summarize")
+    workflow.add_edge("transcribe", "moderate")
+    workflow.add_edge("moderate", "summarize")
     workflow.add_edge("summarize", "score")
     workflow.add_edge("score", END)