Update app.py

app.py

@@ -18,10 +18,10 @@ if not hf_token:
 login(token=hf_token)
 
 # Initialize session state for timer
-if 'timer_started' not in st.session_state:
-    st.session_state.timer_started = False
-if 'timer_frozen' not in st.session_state:
-    st.session_state.timer_frozen = False
+#if 'timer_started' not in st.session_state:
+    #st.session_state.timer_started = False
+#if 'timer_frozen' not in st.session_state:
+    #st.session_state.timer_frozen = False
 
 # Timer component using HTML and JavaScript
 def timer():
@@ -57,79 +57,90 @@ st.write("This model will score your reviews in your CSV file and generate a rep
 
 # Load models with caching to avoid reloading on every run
 @st.cache_resource
+@st.cache_resource
 def load_models():
-    # Load the scoring model via pipeline.
-    score_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1", device=0)
-    # Load the Gemma text generation pipeline.
-    gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it", device=0)
+    try:
+        score_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1", device=0)
+    except Exception as e:
+        st.error(f"Error loading score model: {e}")
+        score_pipe = None
+    try:
+        gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it", device=0)
+    except Exception as e:
+        st.error(f"Error loading Gemma model: {e}")
+        gemma_pipe = None
     return score_pipe, gemma_pipe
 
+
 score_pipe, gemma_pipe = load_models()
 
 # Input: Query text for scoring and CSV file upload for candidate reviews
 query_input = st.text_area("Enter your query text for analysis (this does not need to be part of the CSV):")
 uploaded_file = st.file_uploader("Upload Reviews CSV File (must contain a 'reviewText' column)", type=["csv"])
 
-candidate_docs = []
-if uploaded_file is not None:
-    try:
-        df = pd.read_csv(uploaded_file)
-        if 'reviewText' not in df.columns:
-            st.error("CSV must contain a 'reviewText' column.")
-        else:
-            candidate_docs = df['reviewText'].dropna().astype(str).tolist()
-    except Exception as e:
-        st.error(f"Error reading CSV file: {e}")
-
-if st.button("Generate Report"):
-    # Reset timer state so that the timer always shows up
-    st.session_state.timer_started = False
-    st.session_state.timer_frozen = False
-    # Display the timer every time
-    html(timer(), height=50)
-    if uploaded_file is None:
-        st.error("Please upload a CSV file.")
-    elif not candidate_docs:
-        st.error("CSV must contain a 'reviewText' column.")
-    elif not query_input.strip():
-        st.error("Please enter a query text!")
-    else:
-        if not st.session_state.timer_started and not st.session_state.timer_frozen:
-            st.session_state.timer_started = True
-            html(timer(), height=50)
-        status_text = st.empty()
-        progress_bar = st.progress(0)
+if score_pipe is None or gemma_pipe is None:
+    st.error("Model loading failed. Please check your model names, token permissions, and GPU configuration.")
+else:
+    candidate_docs = []
+    if uploaded_file is not None:
         try:
-            # Stage 1: Score candidate documents using the provided query.
-            status_text.markdown("**🔍 Scoring candidate documents...**")
-            progress_bar.progress(0)
-            
-            scored_docs = []
-            for doc in candidate_docs:
-                combined_text = f"Query: {query_input} Document: {doc}"
-                result = score_pipe(combined_text)[0]
-                scored_docs.append((doc, result["score"]))
-            
-            progress_bar.progress(50)
-            
-            # Stage 2: Generate Report using Gemma, including query and scored results.
-            status_text.markdown("**📝 Generating report with Gemma...**")
-            prompt = f"""
-Generate a detailed report based on the following analysis.
-Query:
-"{query_input}"
-Candidate Reviews with their scores:
-{scored_docs}
-Please provide a concise summary report explaining the insights derived from these scores.
-"""
-            report = gemma_pipe(prompt, max_length=200)
-            progress_bar.progress(100)
-            status_text.success("**✅ Generation complete!**")
-            html("<script>localStorage.setItem('freezeTimer', 'true');</script>", height=0)
-            st.session_state.timer_frozen = True
-            st.write("**Scored Candidate Reviews:**", scored_docs)
-            st.write("**Generated Report:**", report[0]['generated_text'])
+            df = pd.read_csv(uploaded_file)
+            if 'reviewText' not in df.columns:
+                st.error("CSV must contain a 'reviewText' column.")
+            else:
+                candidate_docs = df['reviewText'].dropna().astype(str).tolist()
         except Exception as e:
-            html("<script>document.getElementById('timer').remove();</script>")
-            status_text.error(f"**❌ Error:** {str(e)}")
-            progress_bar.empty()
+            st.error(f"Error reading CSV file: {e}")
+    
+    if st.button("Generate Report"):
+        # Reset timer state so that the timer always shows up
+        st.session_state.timer_started = False
+        st.session_state.timer_frozen = False
+        # Display the timer every time
+        html(timer(), height=50)
+        if uploaded_file is None:
+            st.error("Please upload a CSV file.")
+        elif not candidate_docs:
+            st.error("CSV must contain a 'reviewText' column.")
+        elif not query_input.strip():
+            st.error("Please enter a query text!")
+        else:
+            if not st.session_state.timer_started and not st.session_state.timer_frozen:
+                st.session_state.timer_started = True
+                html(timer(), height=50)
+            status_text = st.empty()
+            progress_bar = st.progress(0)
+            try:
+                # Stage 1: Score candidate documents using the provided query.
+                status_text.markdown("**🔍 Scoring candidate documents...**")
+                progress_bar.progress(0)
+                
+                scored_docs = []
+                for doc in candidate_docs:
+                    combined_text = f"Query: {query_input} Document: {doc}"
+                    result = score_pipe(combined_text)[0]
+                    scored_docs.append((doc, result["score"]))
+                
+                progress_bar.progress(50)
+                
+                # Stage 2: Generate Report using Gemma, including query and scored results.
+                status_text.markdown("**📝 Generating report with Gemma...**")
+                prompt = f"""
+    Generate a detailed report based on the following analysis.
+    Query:
+    "{query_input}"
+    Candidate Reviews with their scores:
+    {scored_docs}
+    Please provide a concise summary report explaining the insights derived from these scores.
+    """
+                report = gemma_pipe(prompt, max_length=200)
+                progress_bar.progress(100)
+                status_text.success("**✅ Generation complete!**")
+                html("<script>localStorage.setItem('freezeTimer', 'true');</script>", height=0)
+                st.session_state.timer_frozen = True
+                st.write("**Scored Candidate Reviews:**", scored_docs)
+                st.write("**Generated Report:**", report[0]['generated_text'])
+            except Exception as e:
+                html("<script>document.getElementById('timer').remove();</script>")
+                status_text.error(f"**❌ Error:** {str(e)}")
+                progress_bar.empty()