feat: add topic prepending and expose invalid keywords output

app.py

@@ -123,7 +123,8 @@ def classify_individual_topic(topic_name: str):
                 valid_set.add(path)
                 
         # Filter generated terms deterministically 
-        valid_kws = [kw for kw in raw_keywords if kw in valid_set]
+        # Prepend the topic string to the final outputs so they present nicely
+        valid_kws = [f"{topic_name} > {kw}" for kw in raw_keywords if kw in valid_set]
         invalid_kws = [kw for kw in raw_keywords if kw not in valid_set]
         return {"predicted_keywords": valid_kws, "invalid_keywords": invalid_kws}
         
@@ -161,20 +162,28 @@ app = workflow.compile()
 # ==========================================================
 async def run_agent_classifier(title, abstract):
     if not title or not abstract:
-        return "Please fill out both Title and Abstract fields.", "N/A"
+        return "Please fill out both Title and Abstract fields.", "N/A", "N/A"
         
     inputs = {"title": title, "abstract": abstract}
     output = await app.ainvoke(inputs)
     
     topics_str = ", ".join(output.get("chosen_topics", []))
     keywords_list = output.get("predicted_keywords", [])
+    invalid_list = output.get("invalid_keywords", [])
     
+    # Format valid output display strings
     if not keywords_list:
         keywords_str = "No explicit keywords mapped."
     else:
         keywords_str = "\n".join([f"• {kw}" for kw in keywords_list])
         
-    return topics_str, keywords_str
+    # Format invalid output display strings
+    if not invalid_list:
+        invalid_str = "None! The agent validation loop passed with 100% data integrity."
+    else:
+        invalid_str = "\n".join([f"⚠ Caught & Removed: {ikw}" for ikw in invalid_list])
+        
+    return topics_str, keywords_str, invalid_str
 
 demo = gr.Interface(
     fn=run_agent_classifier,
@@ -184,7 +193,8 @@ demo = gr.Interface(
     ],
     outputs=[
         gr.Textbox(label="Routed Multi-Topic Domains"),
-        gr.Textbox(label="Verified GCMD Keywords Extracted")
+        gr.Textbox(label="Verified GCMD Keywords Extracted (with Topics)"),
+        gr.Textbox(label="Hallucinated/Invalid Keywords Caught and Removed")
     ],
     title="GCMD Science Keyword Classifier Agent",
     description="Proof of Concept using LangGraph and LangChain. Routes articles concurrently across science domains and runs isolated self-validation routines.",