Update app.py

app.py

@@ -57,8 +57,8 @@ st.header("Sentiment Analysis & Report Generation with Gemma")
 # Introduction for the Hugging Face interface
 st.write("""
 Welcome to the Sentiment Analysis & Report Generator app!
-This tool leverages Hugging Face’s models to analyze your text by reranking candidate documents based on a query,
-and then generates a detailed report explaining key insights.
+This tool leverages Hugging Face’s models to analyze your text by scoring candidate documents based on a query.
+The input along with their scores is then used to generate a detailed report explaining key insights.
 You can either paste your query text directly into the text area and optionally upload a CSV file containing candidate documents.
 If no CSV is provided, the query text will be split into sentences to serve as candidate documents.
 """)
@@ -66,7 +66,7 @@ If no CSV is provided, the query text will be split into sentences to serve as c
 # Load models with caching to avoid reloading on every run
 @st.cache_resource
 def load_models():
-    # Load the reranker model via pipeline.
+    # Load the text-classification pipeline (acting as our scoring model).
     sentiment_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1")
     # Load the Gemma text generation pipeline.
     gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it", use_auth_token=hf_token)
@@ -107,24 +107,28 @@ if st.button("Generate Report"):
         status_text = st.empty()
         progress_bar = st.progress(0)
         try:
-            # Stage 1: Reranking analysis using the model's rank method.
-            status_text.markdown("**🔍 Running reranking analysis...**")
+            # Stage 1: Score candidate documents without reranking.
+            status_text.markdown("**🔍 Scoring candidate documents...**")
             progress_bar.progress(0)
-            # Use the pipeline's underlying model to rank candidate documents with the given query.
-            # Note: We access the model via sentiment_pipe.model.
-            results = sentiment_pipe.rank(query_input, candidate_docs, return_documents=True, top_k=3)
+            
+            # Create query-document pairs and score each pair.
+            scored_docs = []
+            for doc in candidate_docs:
+                combined_text = f"Query: {query_input} Document: {doc}"
+                result = sentiment_pipe(combined_text)[0]
+                # Append the document along with its score.
+                scored_docs.append((doc, result["score"]))
+            
             progress_bar.progress(50)
             
-            # Stage 2: Generate Report using Gemma, using the reranking result.
+            # Stage 2: Generate Report using Gemma, using the scored candidate documents.
             status_text.markdown("**📝 Generating report with Gemma...**")
             prompt = f"""
 Generate a detailed report based on the following analysis.
 Query:
 "{query_input}"
-Candidate Documents:
-{candidate_docs}
-Reranking Analysis Result (Top 3):
-{results}
+Candidate Documents with their scores:
+{scored_docs}
 Please provide a concise summary report explaining the insights derived from this analysis.
 """
             report = gemma_pipe(prompt, max_length=200)
@@ -132,9 +136,9 @@ Please provide a concise summary report explaining the insights derived from thi
             status_text.success("**✅ Generation complete!**")
             html("<script>localStorage.setItem('freezeTimer', 'true');</script>", height=0)
             st.session_state.timer_frozen = True
-            st.write("**Reranking Analysis Result:**", results)
+            st.write("**Scored Candidate Documents:**", 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()
+            progress_bar.empty()