Update app.py

app.py

@@ -1,95 +1,95 @@
-import os
-from crewai import Agent, Task, Crew
-from langchain_groq import ChatGroq
-import streamlit as st
-from PIL import Image
-
-# Initialize the LLM for the Einstein Agent
-llm = ChatGroq(
-    groq_api_key="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",
-    model_name="llama3-70b-8192",  # Replace with the actual Einstein model name
-)
-
-# Define the Einstein Agent with a research-oriented goal
-einstein_agent = Agent(
-    role='Einstein Agent',
-    goal='Provide in-depth answers and insights on various topics to help with research questions.',
-    backstory=(
-        "You are an Einstein Agent, skilled in gathering and synthesizing information across domains. Mainly in Physics. "
-        "Your role is to answer questions with a detailed and analytical approach."
-    ),
-    verbose=True,
-    llm=llm,
-)
-
-def process_question_with_agent(question):
-    # Describe the task for the agent
-    task_description = f"Research and provide a detailed answer to the question: '{question}'"
-    
-    # Define the task for the agent to generate a response to the question
-    research_task = Task(
-        description=task_description,
-        agent=einstein_agent,
-        human_input=False,
-        expected_output="According to user need response to the question"  # Placeholder for expected output
-    )
-
-    # Instantiate the crew with the defined agent and task
-    crew = Crew(
-        agents=[einstein_agent],
-        tasks=[research_task],
-        verbose=2,
-    )
-
-    # Get the crew to work on the task and return the result
-    result = crew.kickoff()
-    
-    return result
-
-# Load the image from the specified path
-image_path = r"C:\Users\PMLS\Downloads\image-removebg-preview (1).png"  # Update with your image path
-image = Image.open(image_path)
-
-# Resize the image to 500x500
-image = image.resize((300, 300))
-
-# Set the title of your app with Markdown
-st.markdown("<h1 style='text-align: center;'>Einstein Researcher Chatbot</h1>", unsafe_allow_html=True)
-
-# Convert the image to base64 for embedding in HTML
-import base64
-from io import BytesIO
-
-buffered = BytesIO()
-image.save(buffered, format="PNG")
-img_str = base64.b64encode(buffered.getvalue()).decode()
-
-# Display the image and center it using HTML
-st.markdown(f"<div style='text-align: center;'><img src='data:image/png;base64,{img_str}' width='300' height='300'/></div>", unsafe_allow_html=True)
-
-# Initialize chat history
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-
-# Display chat messages from history on app rerun
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
-
-# React to user input
-if prompt := st.chat_input("Ask a research question:"):
-    # Display user message in chat message container
-    st.chat_message("user").markdown(prompt)
-    # Add user message to chat history
-    st.session_state.messages.append({"role": "user", "content": prompt})
-
-    # Get the response from the Einstein Agent
-    with st.spinner("Processing..."):
-        response = process_question_with_agent(prompt)
-    
-    # Display assistant response in chat message container
-    with st.chat_message("assistant"):
-        st.markdown(response)
-    
-    # Add assistant response to chat history
-    st.session_state.messages.append({"role": "assistant", "content": response})
+import os
+from crewai import Agent, Task, Crew
+from langchain_groq import ChatGroq
+import streamlit as st
+from PIL import Image
+
+# Initialize the LLM for the Einstein Agent
+llm = ChatGroq(
+    groq_api_key="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",
+    model_name="llama3-70b-8192",  # Replace with the actual Einstein model name
+)
+
+# Define the Einstein Agent with a research-oriented goal
+einstein_agent = Agent(
+    role='Einstein Agent',
+    goal='Provide in-depth answers and insights on various topics to help with research questions.',
+    backstory=(
+        "You are an Einstein Agent, skilled in gathering and synthesizing information across domains. Mainly in Physics. "
+        "Your role is to answer questions with a detailed and analytical approach."
+    ),
+    verbose=True,
+    llm=llm,
+)
+
+def process_question_with_agent(question):
+    # Describe the task for the agent
+    task_description = f"Research and provide a detailed answer to the question: '{question}'"
+    
+    # Define the task for the agent to generate a response to the question
+    research_task = Task(
+        description=task_description,
+        agent=einstein_agent,
+        human_input=False,
+        expected_output="According to user need response to the question"  # Placeholder for expected output
+    )
+
+    # Instantiate the crew with the defined agent and task
+    crew = Crew(
+        agents=[einstein_agent],
+        tasks=[research_task],
+        verbose=2,
+    )
+
+    # Get the crew to work on the task and return the result
+    result = crew.kickoff()
+    
+    return result
+
+# Load the image from the specified path
+image_path = "/image-removebg-preview (1).png"  # Update with your image path
+image = Image.open(image_path)
+
+# Resize the image to 500x500
+image = image.resize((300, 300))
+
+# Set the title of your app with Markdown
+st.markdown("<h1 style='text-align: center;'>Einstein Researcher Chatbot</h1>", unsafe_allow_html=True)
+
+# Convert the image to base64 for embedding in HTML
+import base64
+from io import BytesIO
+
+buffered = BytesIO()
+image.save(buffered, format="PNG")
+img_str = base64.b64encode(buffered.getvalue()).decode()
+
+# Display the image and center it using HTML
+st.markdown(f"<div style='text-align: center;'><img src='data:image/png;base64,{img_str}' width='300' height='300'/></div>", unsafe_allow_html=True)
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# React to user input
+if prompt := st.chat_input("Ask a research question:"):
+    # Display user message in chat message container
+    st.chat_message("user").markdown(prompt)
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    # Get the response from the Einstein Agent
+    with st.spinner("Processing..."):
+        response = process_question_with_agent(prompt)
+    
+    # Display assistant response in chat message container
+    with st.chat_message("assistant"):
+        st.markdown(response)
+    
+    # Add assistant response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": response})