Update app.py

app.py

@@ -1,32 +1,13 @@
 import gradio as gr
 import os
-import logging
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_core.output_parsers import StrOutputParser
-from langchain_openai import ChatOpenAI
-from langchain_community.graphs import Neo4jGraph
-from typing import List, Tuple
-from pydantic import BaseModel, Field
-from langchain_core.messages import AIMessage, HumanMessage
-from langchain_core.runnables import (
-    RunnableBranch,
-    RunnableLambda,
-    RunnablePassthrough,
-    RunnableParallel,
-)
-from langchain_core.prompts.prompt import PromptTemplate
 import requests
 import tempfile
-from langchain.memory import ConversationBufferWindowMemory
-import time
-import logging
-from langchain.chains import ConversationChain
 import torch
-import torchaudio
-from transformers import pipeline, AutoModelForSpeechSeq2Seq, AutoProcessor
 import numpy as np
-import threading
-
+from transformers import pipeline, AutoModelForSpeechSeq2Seq, AutoProcessor
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain_community.graphs import Neo4jGraph
 
 # Setup Neo4j
 graph = Neo4jGraph(
@@ -35,10 +16,9 @@ graph = Neo4jGraph(
     password="Z10duoPkKCtENuOukw3eIlvl0xJWKtrVSr-_hGX1LQ4"
 )
 
-# Define a prompt template for generating responses
-template = """I am a guide for Birmingham, Alabama. I can provide recommendations and insights about the city, including events and activities.
-Ask your question directly, and I'll provide a precise and quick,short and crisp response in a conversational way without any Greet.
-{context}
+# Define a concise prompt template for generating responses
+template = """I am a guide for Birmingham, Alabama. I will provide a precise and short response based solely on the provided data.
+Do not include any additional commentary or context.
 
 Data:
 {context}
@@ -71,6 +51,11 @@ def get_response(question):
         context = retrieve_from_neo4j(question)
         prompt = qa_prompt.format_prompt(context=context, question=question)
         response = chat_model(prompt.to_string())
+        
+        # Filter extraneous content, keeping only the answer part
+        if "Answer:" in response:
+            response = response.split("Answer:")[-1].strip()  # Extract the part after "Answer:" and strip extra spaces
+        
         return response
     except Exception as e:
         return f"Error: {str(e)}"
@@ -141,4 +126,4 @@ with gr.Blocks() as demo:
     )
 
 # Launch the Gradio interface
-demo.launch(show_error=True, share=True)
+demo.launch(show_error=True, share=True)