Update app.py

app.py

@@ -360,46 +360,58 @@ def get_contextual_search_result(target_word, tar_passage, groq_client_instance,
         return "Contextual search requires the LLM API. Please set up your GROQ_API_KEY."
 
     # Basic check if word exists (optional, LLM can handle it too)
-    if target_word.lower() not in tar_passage.lower():
-        return f"The term '{target_word}' was not found in the manifesto text."
+    # Simple check, might generate false positives/negatives
+    # if target_word.lower() not in tar_passage.lower():
+    #     return f"The term '{target_word}' was not found in the manifesto text."
 
     # Truncate passage if too long for the model/context window
-    # You might need to adjust this based on your model's limits and desired performance
-    if len(tar_passage) > max_context_length:
+    original_length = len(tar_passage)
+    if original_length > max_context_length:
         # Simple truncation; could be improved to ensure sentences are complete
-        tar_passage = tar_passage[:max_context_length]
-        print(f"Warning: Passage truncated for LLM search context to {max_context_length} characters.")
+        tar_passage_truncated = tar_passage[:max_context_length]
+        print(f"Warning: Passage truncated for LLM search context from {original_length} to {max_context_length} characters.")
+    else:
+        tar_passage_truncated = tar_passage
 
+    # --- Improved Prompt ---
     prompt = f"""
-    You are given a political manifesto text and a specific search term.
-    Your task is to find all relevant mentions of the search term in the text and provide a concise, informative summary of the context surrounding each mention.
-    Focus on the key ideas, policies, or points related to the search term.
-    If the term is not found or not relevant, state that clearly.
-    Search Term: {target_word}
-    Manifesto Text:
-    {tar_passage}
-    """
+You are an expert political analyst. You have been given a section of a political manifesto and a specific search term.
+Your task is to extract and summarize all information related to the search term from the provided text.
+Focus on:
+1.  Specific policies, promises, or statements related to the term.
+2.  The context in which the term is used.
+3.  Any key details, figures, or commitments mentioned.
+Present your findings concisely. If the term is not relevant or not found in the provided text section, state that clearly.
+Search Term: {target_word}
+Manifesto Text Section:
+{tar_passage_truncated}
+Relevant Information:
+"""
 
     try:
         completion = groq_client_instance.chat.completions.create(
             model="llama3-8b-8192", # Use the same or a suitable model
             messages=[
-                {"role": "system", "content": "You are a helpful assistant skilled at analyzing political texts and extracting relevant information based on a search query."},
+                {"role": "system", "content": "You are a helpful assistant skilled at analyzing political texts and extracting relevant information based on a search query. Provide clear, concise summaries."},
                 {"role": "user", "content": prompt}
             ],
             temperature=0.2, # Low temperature for more factual extraction
             max_tokens=1000  # Adjust based on expected output length
         )
         result = completion.choices[0].message.content.strip()
-        return result if result else f"No specific context for '{target_word}' could be generated."
+        # Add a note if the input was truncated
+        if original_length > max_context_length:
+             result = f"(Note: Analysis based on the first {max_context_length} characters of the manifesto.)\n\n" + result
+        return result if result else f"No specific context for '{target_word}' could be generated from the provided text section."
     except Exception as e:
         error_msg = f"Error during contextual search for '{target_word}': {str(e)}"
         print(error_msg)
         traceback.print_exc()
         # Fallback to concordance if LLM fails?
-        # return get_all_phases_containing_tar_wrd_fallback(target_word, tar_passage)
+        # return get_all_phases_containing_tar_wrd(target_word, tar_passage)
         return error_msg # Or return the error message directly
 
+
 def analysis(Manifesto, Search):
     try:
         if Manifesto is None:
@@ -412,10 +424,10 @@ def analysis(Manifesto, Search):
             return raw_party, {}, None, None, None, None, None, "Parsing failed"
         text_Party = clean_text(raw_party)
         text_Party_processed = Preprocess(text_Party)
-        
+
         # --- Perform Search FIRST using the ORIGINAL text for better context ---
         # Pass the original raw text for richer context to the LLM
-        searChRes = get_contextual_search_result(Search, raw_party, groq_client) 
+        searChRes = get_contextual_search_result(Search, raw_party, groq_client)
 
         # --- Then proceed with other analyses ---
         summary = generate_summary(raw_party) # Use raw_party for summary for more context?
@@ -438,12 +450,10 @@ def analysis(Manifesto, Search):
         sentiment_plot = safe_plot(lambda: df_dummy['Polarity_Label'].value_counts().plot(kind='bar', color="#FF9F45", title='Sentiment Analysis'))
         subjectivity_plot = safe_plot(lambda: df_dummy['Subjectivity_Label'].value_counts().plot(kind='bar', color="#B667F1", title='Subjectivity Analysis'))
         freq_plot = fDistancePlot(text_Party_processed)
-        dispersion_plot = DispersionPlot(text_Party_processed)
+        dispersion_plot = DispersionPlot(text_Party_processed) # Use fixed version
         wordcloud = word_cloud_generator(Manifesto, text_Party_processed) # Pass Manifesto object itself
         fdist_Party = fDistance(text_Party_processed)
-        
-        # searChRes is now generated earlier
-        
+
         return searChRes, fdist_Party, sentiment_plot, subjectivity_plot, wordcloud, freq_plot, dispersion_plot, summary
 
     except Exception as e:
@@ -455,7 +465,6 @@ def analysis(Manifesto, Search):
 
 
 # --- Gradio Interface (remains largely the same, just ensuring output variable names match) ---
-# Use Blocks for custom layout
 with gr.Blocks(title='Manifesto Analysis') as demo:
     gr.Markdown("# Manifesto Analysis")
     # Input Section
@@ -519,6 +528,7 @@ with gr.Blocks(title='Manifesto Analysis') as demo:
     )
 
     # --- Examples ---
+    # Ensure outputs list references the PREDEFINED components from the layout
     gr.Examples(
         examples=[
             ["Example/AAP_Manifesto_2019.pdf", "government"],
@@ -526,11 +536,11 @@ with gr.Blocks(title='Manifesto Analysis') as demo:
             ["Example/Congress_Manifesto_2019.pdf", "safety"]
         ],
         inputs=[file_input, search_input],
-        outputs=[search_output, topics_output, sentiment_output, subjectivity_output, wordcloud_output, freq_output, dispersion_output, summary_output], # Link examples to outputs
+        # --- Key Fix: Reference the predefined output components ---
+        outputs=[search_output, topics_output, sentiment_output, subjectivity_output, wordcloud_output, freq_output, dispersion_output, summary_output],
         fn=analysis # Run analysis on example click
     )
 
-# Launch the app
-if __name__ == "__main__":
-    demo.launch(debug=True, share=False, show_error=True)
 
+if __name__ == "__main__":
+    demo.launch(debug=True, share=False, show_error=True)