Update app.py

app.py

@@ -1,5 +1,3 @@
-import os
-from dotenv import load_dotenv
 import streamlit as st
 from langchain_groq import ChatGroq
 from langchain.chains import LLMChain
@@ -9,42 +7,33 @@ from langchain.agents.agent_types import AgentType
 from langchain.agents import Tool, initialize_agent
 from langchain.callbacks import StreamlitCallbackHandler
 
-# Load environment variables from the .env file
-load_dotenv()
+# Set up Streamlit page configuration
+st.set_page_config(page_title="General Knowledge Assistant", page_icon="🧭")
+st.title("General Knowledge Assistant")
 
-# Get API key from environment variables
-groq_api_key = os.getenv("GROQ_API_KEY")
+# API Key input for Groq
+groq_api_key = st.sidebar.text_input(label="Groq API Key", type="password")
 
-# If the API key is not set, show an info message and stop execution
 if not groq_api_key:
-    st.info("Please set your Groq API key in the .env file to continue")
+    st.info("Please add your Groq API key to continue")
     st.stop()
 
-# Set up Streamlit page configuration
-st.set_page_config(page_title="General Knowledge Assistant")
-st.title("General Knowledge Assistant")
-
-# Initialize the LLM (Groq API - deepseek-r1-distill-llama-70b)
-llm = ChatGroq(model="deepseek-r1-distill-llama-70b", groq_api_key=groq_api_key)
+# Initialize the LLM (Groq API - llama-3.1-70b)
+llm = ChatGroq(model="meta-llama/llama-4-maverick-17b-128e-instruct", groq_api_key=groq_api_key)
 
 # Initialize Wikipedia tool for information retrieval
 wikipedia_wrapper = WikipediaAPIWrapper()
 wikipedia_tool = Tool(
     name="Wikipedia",
     func=wikipedia_wrapper.run,
-    description="A tool for searching Wikipedia to retrieve up-to-date and detailed information on various topics."
+    description="A tool for searching the Internet to find information on various topics, including general knowledge."
 )
 
-# Updated prompt template with explicit instructions for ReAct chaining
+# Prompt template for general knowledge questions
 prompt = """
-You are a knowledgeable assistant. Your task is to answer the user's questions accurately using your general knowledge.
-If you believe that your internal knowledge may be outdated or insufficient, follow these steps:
-1. Write your internal thought process beginning with 'Thought:'.
-2. If you determine that you need updated information, output an 'Action:' line in the following format:
-   Action: Wikipedia[search query]
-3. Once you receive additional information, integrate it into your final answer.
-Ensure that you follow this format strictly. Also, whenever I ask you to write an essay, provide a title for the essay.
-
+You are a knowledgeable assistant. Your task is to answer the user's questions accurately, using your general knowledge.
+If the answer is not readily available in your knowledge base, search Wikipedia for relevant information.
+Your information should be accurate and up to date.Whenever I tell you to write essay give a title also to the essay.
 Question: {question}
 Answer:
 """
@@ -62,7 +51,7 @@ chain = LLMChain(llm=llm, prompt=prompt_template)
 reasoning_tool = Tool(
     name="Reasoning tool",
     func=chain.run,
-    description="A tool for answering general knowledge questions using logical reasoning and factual information. Use this tool and consult Wikipedia if necessary."
+    description="A tool for answering general knowledge questions using logical reasoning and factual information.Try to use the latest information"
 )
 
 # Initialize the agent with the tools and LLM
@@ -82,25 +71,25 @@ if "messages" not in st.session_state:
 
 # Display the conversation history
 for msg in st.session_state.messages:
-    st.chat_message(msg["role"]).write(msg["content"])
+    st.chat_message(msg["role"]).write(msg['content'])
 
 # Get the user's question
 question = st.text_area("Enter your question:", "Please enter your general knowledge question here")
 
 # Handle the button click to process the question
-if st.button("Find my answer"):
+if st.button("find my answer"):
     if question:
-        with st.spinner("Generating response..."):
-            # Append the user question to the conversation history and display it
-            st.session_state.messages.append({"role": "user", "content": question})
+        with st.spinner("Generate response.."):
+            st.session_state.messages.append({"role":"user","content":question})
             st.chat_message("user").write(question)
 
-            st_cb = StreamlitCallbackHandler(st.container(), expand_new_thoughts=False)
-            # Pass the question string directly to the agent (instead of the full conversation history)
-            response = assistant_agent.run(question, callbacks=[st_cb])
-            st.session_state.messages.append({'role': 'assistant', "content": response})
-            
+            st_cb=StreamlitCallbackHandler(st.container(),expand_new_thoughts=False)
+            response=assistant_agent.run(st.session_state.messages,callbacks=[st_cb]
+                                         )
+            st.session_state.messages.append({'role':'assistant',"content":response})
             st.write('### Response:')
             st.success(response)
+
     else:
-        st.warning("Please enter your question")
+        st.warning("Please enter the question")
+