cp

app.py

@@ -41,21 +41,23 @@
 #     for entity in entities:
 #         st.write(f"Entity: {entity['word']}, Entity Type: {entity['entity_group']}")
 
-
 import streamlit as st
 from transformers import pipeline
 
-# Load CodeBERT model as a feature extractor
-# (Note: You may need to adjust the task if using CodeBERT for other specific purposes)
-codebert = pipeline("feature-extraction", model="microsoft/codebert-base")
+# Load a smaller LLaMA model with permission to run custom code
+text_generator = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
+
+st.title('General Query Answerer')
+
+# User input for a general question
+user_query = st.text_area("Enter your question:", "Name all 50 US states.")
+
+# Generate answer
+if st.button('Answer Question'):
+    answer = text_generator(user_query, max_length=150)[0]['generated_text']
+    # Display the answer
+    st.write('Answer:', answer)
+
 
-st.title('CodeBERT Feature Extractor')
 
-# User input for text
-user_input = st.text_area("Enter code or text to extract features:", "SELECT * FROM users;")
 
-# Extract features
-if st.button('Extract Features'):
-    features = codebert(user_input)
-    # Display extracted features (example: show size of feature vector for demonstration)
-    st.write('Number of features extracted:', len(features[0][0]))