Update app.py

app.py

@@ -1,6 +1,7 @@
 import os
 import json
 import gradio as gr
+import pandas as pd
 from tempfile import NamedTemporaryFile
 
 from langchain_core.prompts import ChatPromptTemplate
@@ -31,6 +32,8 @@ prompt = """
 Answer the question based only on the following context:
 {context}
 Question: {question}
+
+Provide a concise and direct answer to the question:
 """
 
 def get_model():
@@ -47,7 +50,7 @@ def generate_chunked_response(model, prompt, max_tokens=500, max_chunks=5):
         full_response += chunk
         if chunk.strip().endswith((".", "!", "?")):
             break
-    return full_response
+    return full_response.strip()
 
 def response(database, model, question):
     prompt_val = ChatPromptTemplate.from_template(prompt)
@@ -77,6 +80,19 @@ def ask_question(question):
     model = get_model()
     return response(database, model, question)
 
+def extract_db_to_excel():
+    embed = get_embeddings()
+    database = FAISS.load_local("faiss_database", embed, allow_dangerous_deserialization=True)
+    
+    documents = database.docstore._dict.values()
+    data = [{"page_content": doc.page_content, "metadata": json.dumps(doc.metadata)} for doc in documents]
+    df = pd.DataFrame(data)
+    
+    excel_path = "database_output.xlsx"
+    df.to_excel(excel_path, index=False)
+    
+    return f"Database extracted to {excel_path}"
+
 with gr.Blocks() as demo:
     gr.Markdown("# Chat with your PDF documents")
     
@@ -93,6 +109,10 @@ with gr.Blocks() as demo:
     
     answer_output = gr.Textbox(label="Answer")
     submit_button.click(ask_question, inputs=[question_input], outputs=answer_output)
+    
+    extract_button = gr.Button("Extract Database to Excel")
+    extract_output = gr.Textbox(label="Extraction Status")
+    extract_button.click(extract_db_to_excel, inputs=[], outputs=extract_output)
 
 if __name__ == "__main__":
     demo.launch()