Update app.py

app.py

@@ -44,11 +44,8 @@ def _extract_json_from_llm(response_text: str) -> dict:
         if match:
             return json.loads(match.group(0))
         return json.loads(response_text)
-    except json.JSONDecodeError:
-        return {
-            "sentiment_score": 0.0, "primary_tone": "neutral", 
-            "primary_theme": "unclear", "tone_scores": {"neutral": 1.0}
-        }
+    except Exception as e:
+        raise ValueError(f"Failed to parse LLM response into JSON. Raw response: {response_text[:150]}...")
 
 def analyze_article(text: str) -> dict:
     """Analyzes framing using an LLM API and calculates readability."""
@@ -68,11 +65,8 @@ def analyze_article(text: str) -> dict:
     "{safe_text}"
     """
     
-    try:
-        response = client.text_generation(prompt, max_new_tokens=250, temperature=0.1)
-        llm_data = _extract_json_from_llm(response)
-    except Exception as e:
-        llm_data = _extract_json_from_llm("") # fallback
+    response = client.text_generation(prompt, max_new_tokens=250, temperature=0.1)
+    llm_data = _extract_json_from_llm(response)
 
     subjectivity_score = TextBlob(safe_text).sentiment.subjectivity
     raw_reading_ease = textstat.flesch_reading_ease(safe_text)
@@ -219,12 +213,9 @@ def check_contradiction(text_a: str, text_b: str) -> dict:
     Text 1: "{text_a[:1000]}"
     Text 2: "{text_b[:1000]}"
     """
-    try:
-        response = client.text_generation(prompt, max_new_tokens=100, temperature=0.1)
-        result = _extract_json_from_llm(response)
-        return {"relationship": result.get("relationship", "NEUTRAL"), "confidence": result.get("confidence", 0.0)}
-    except:
-        return {"relationship": "NEUTRAL", "confidence": 0.0}
+    response = client.text_generation(prompt, max_new_tokens=100, temperature=0.1)
+    result = _extract_json_from_llm(response)
+    return {"relationship": result.get("relationship", "NEUTRAL"), "confidence": result.get("confidence", 0.0)}
     
 
 # USER INTERFACE
@@ -307,14 +298,20 @@ if st.button("Analyze and Compare Sources", use_container_width=True, type="prim
     
     else:
         with st.spinner("Analyzing framing semantics for both sources."):
-            with concurrent.futures.ThreadPoolExecutor() as executor:
-                future_a = executor.submit(analyze_article, text_a_clean)
-                future_b = executor.submit(analyze_article, text_b_clean)
-                future_nli = executor.submit(check_contradiction, text_a_clean, text_b_clean)
-                
-                st.session_state.results_a = future_a.result()
-                st.session_state.results_b = future_b.result()
-                st.session_state.nli_result = future_nli.result()
+            try:
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    future_a = executor.submit(analyze_article, text_a_clean)
+                    future_b = executor.submit(analyze_article, text_b_clean)
+                    future_nli = executor.submit(check_contradiction, text_a_clean, text_b_clean)
+                    
+                    st.session_state.results_a = future_a.result()
+                    st.session_state.results_b = future_b.result()
+                    st.session_state.nli_result = future_nli.result()
+            except Exception as e:
+                st.error(f"API or Processing Error: {str(e)}")
+                st.session_state.results_a = None
+                st.session_state.results_b = None
+                st.session_state.nli_result = None
 
 # Analysis Display
 if st.session_state.results_a and st.session_state.results_b: