Update app.py

app.py

@@ -1,26 +1,25 @@
-# app.py
-
 import os
 from dotenv import load_dotenv
 from tavily import TavilyClient
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.chains import LLMChain
 from langchain.prompts import PromptTemplate
+import streamlit as st
 
-# 1. Load environment variables from .env file (if present)
+# Load .env
 load_dotenv()
 
-# 2. Set API keys from environment
-GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY")
-TAVILY_API_KEY = os.environ.get("TAVILY_API_KEY")
+# API keys
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+TAVILY_API_KEY = os.getenv("TAVILY_API_KEY")
 
-# 3. Initialize Gemini LLM
+# LLM
 llm = ChatGoogleGenerativeAI(
     model="models/gemini-1.5-flash",
     google_api_key=GOOGLE_API_KEY
 )
 
-# 4. Tavily Client
+# Tavily
 tavily_client = TavilyClient(api_key=TAVILY_API_KEY)
 
 def extract_website_text(url):
@@ -29,7 +28,7 @@ def extract_website_text(url):
         return result[0]["text"]
     return "Could not extract content from the URL."
 
-# 5. Prompt Template
+# Prompt
 prompt = PromptTemplate(
     input_variables=["website_content", "question"],
     template="""
@@ -42,25 +41,19 @@ Answer the following question:
 """
 )
 
-# 6. LLM QA Chain
 qa_chain = LLMChain(llm=llm, prompt=prompt)
 
-# 7. Main Chat Function
-def ask_from_website(url, question):
-    print(f"\n🔗 Extracting content from: {url}")
-    website_text = extract_website_text(url)
-    
-    print(f"\n💬 Asking: {question}")
-    response = qa_chain.invoke({
-        "website_content": website_text,
-        "question": question
-    })
-
-    print("\n✅ Answer:")
-    print(response["text"])
-
-# 8. Run
-if __name__ == "__main__":
-    url = input("Enter the website URL: ")
-    question = input("What do you want to ask about this website? ")
-    ask_from_website(url, question)
+# Streamlit UI
+st.title("🌐 WebQueryBot – Ask any website!")
+url = st.text_input("Enter a website URL:")
+question = st.text_area("What do you want to ask about the website?")
+
+if st.button("Get Answer"):
+    with st.spinner("Extracting and generating answer..."):
+        site_text = extract_website_text(url)
+        result = qa_chain.invoke({
+            "website_content": site_text,
+            "question": question
+        })
+        st.subheader("✅ Answer")
+        st.write(result["text"])