Update app.py

app.py

@@ -7,6 +7,7 @@ import numpy as np
 
 # Load a lightweight NLP model for query understanding
 nlp = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")  # Model for summarization
 
 # Function to load the uploaded file (CSV or Excel)
 def load_file(uploaded_file):
@@ -32,6 +33,22 @@ def classify_query(query, candidate_labels):
         return results['labels'][0]
     return None
 
+# Function to summarize document content
+def summarize_document(data):
+    """Generate a summary for the document."""
+    if data is None:
+        return "No data loaded."
+    
+    # Convert the dataframe to a string representation for summarization
+    document_text = data.to_string(index=False)
+    
+    # Summarize the document text using the summarizer
+    try:
+        summary = summarizer(document_text, max_length=150, min_length=50, do_sample=False)
+        return summary[0]['summary_text']
+    except Exception as e:
+        return f"Error summarizing document: {e}"
+
 # Function to generate a graph based on user query
 def generate_graph(data, query):
     """Generate a graph based on user query."""
@@ -99,6 +116,12 @@ def generate_graph(data, query):
             else:
                 response += " Could not find relevant 'department' or 'sales' columns in the dataset."
 
+        elif query.lower() == "what is this document":
+            # Provide a document summary
+            response = "Analyzing the document content."
+            document_summary = summarize_document(data)
+            response += f" Here is a summary of the document: {document_summary}"
+
         elif query_type == "general question":
             # Handle general questions
             response = "Analyzing the data for your general question."
@@ -159,7 +182,7 @@ def main():
             st.write("Dataset preview:", data.head())
 
             # User input for query
-            user_query = st.text_input("Enter your query (e.g., 'Generate a bar chart for countries and sales', or 'Which country has the highest sales?')")
+            user_query = st.text_input("Enter your query (e.g., 'Generate a bar chart for countries and sales', or 'What is this document?')")
 
             if user_query:
                 # Generate the graph based on the query or handle general questions