Update app.py

app.py

@@ -1,13 +1,17 @@
 import os
-from langchain_huggingface import HuggingFaceEndpoint
+import requests
 import streamlit as st
+from langchain_huggingface import HuggingFaceEndpoint
 from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser
-import requests
+from transformers import pipeline  # for Sentiment Analysis
 from config import NASA_API_KEY  # Import the NASA API key from the configuration file
 
 model_id = "mistralai/Mistral-7B-Instruct-v0.3"
 
+# Initialize sentiment analysis pipeline
+sentiment_analyzer = pipeline("sentiment-analysis")
+
 def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.1):
     llm = HuggingFaceEndpoint(
         repo_id=model_id,
@@ -29,9 +33,30 @@ def get_nasa_apod():
     else:
         return "I couldn't fetch data from NASA right now. Please try again later."
 
+def analyze_sentiment(user_text):
+    """
+    Analyzes the sentiment of the user's input to adjust responses.
+    """
+    result = sentiment_analyzer(user_text)[0]
+    sentiment = result['label']
+    return sentiment
+
+def predict_action(user_text):
+    """
+    Predicts actions based on user input (e.g., fetch space info or general knowledge).
+    """
+    if "NASA" in user_text or "space" in user_text:
+        return "nasa_info"
+    if "weather" in user_text:
+        return "weather_info"
+    return "general_query"
+
 def get_response(system_message, chat_history, user_text, 
                  eos_token_id=['User'], max_new_tokens=256, get_llm_hf_kws={}):
-    if "NASA" in user_text or "space" in user_text:
+    sentiment = analyze_sentiment(user_text)
+    action = predict_action(user_text)
+
+    if action == "nasa_info":
         nasa_response = get_nasa_apod()
         chat_history.append({'role': 'user', 'content': user_text})
         chat_history.append({'role': 'assistant', 'content': nasa_response})
@@ -53,6 +78,11 @@ def get_response(system_message, chat_history, user_text,
 
     chat_history.append({'role': 'user', 'content': user_text})
     chat_history.append({'role': 'assistant', 'content': response})
+
+    # Modify response based on sentiment analysis (e.g., offer help for negative sentiments)
+    if sentiment == "NEGATIVE":
+        response = "I'm sorry to hear that. How can I assist you further?"
+
     return response, chat_history
 
 # Streamlit setup