Create app.py

app.py

@@ -0,0 +1,50 @@
+import streamlit as st
+from transformers import pipeline
+from scraping_utils import scrape_farnell, scrape_digikey
+
+# Load an open-source conversational model
+chatbot = pipeline("conversational", model="microsoft/DialoGPT-medium")
+
+# Streamlit app
+st.title("Electronics Component Chatbot")
+st.write("Ask me anything about electronics components!")
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# Accept user input
+if prompt := st.chat_input("What is your question?"):
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    # Check if the user is asking for component data
+    if "datasheet" in prompt.lower() or "component" in prompt.lower():
+        # Extract component name from the prompt
+        component_name = prompt.replace("datasheet", "").replace("component", "").strip()
+        
+        # Scrape data from Farnell and DigiKey
+        farnell_data = scrape_farnell(component_name)
+        digikey_data = scrape_digikey(component_name)
+        
+        # Combine and display results
+        response = "Here are the components I found:\n\n"
+        for data in farnell_data + digikey_data:
+            response += f"**Name:** {data['name']}\n"
+            response += f"**Description:** {data['description']}\n"
+            response += f"**Datasheet:** [Link]({data['datasheet_link']})\n\n"
+    else:
+        # Get chatbot response for general queries
+        response = chatbot(prompt)[0]['generated_text']
+    
+    # Add chatbot response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": response})
+    with st.chat_message("assistant"):
+        st.markdown(response)