switching to streamlit for demonstration purposes

app.py

@@ -1,19 +1,42 @@
-import streamlit as st
+#import streamlit as st
+import gradio as gr
 from transformers import pipeline
-import gc
+from huggingface_hub import InferenceClient
+#import gc
 
-st.header("Sentiment-demo-app")
-st.subheader("Please be patient and wait up to a minute until the demo app is loaded.")
-st.caption("This is a very simple demo application for a zero-shot classification pipeline to classify positive, neutral, or negative sentiment for a short text. Enter your text in the box below and press CTRl+ENTER to run the model.")
+#st.header("Sentiment-demo-app")
+#st.subheader("Please be patient and wait up to a minute until the demo app is loaded.")
+#st.caption("This is a very simple demo application for a zero-shot classification pipeline to classify positive, neutral, or negative sentiment for a short text. Enter your text in the box below and press CTRl+ENTER to run the model.")
 
-pipe = pipeline("text-classification", model='tabularisai/multilingual-sentiment-analysis') #"zero-shot-classification" model='facebook/bart-large-mnli')
+title = "Sentiment-demo-app"
+description = """This is a very simple demo application for a zero-shot classification pipeline to classify positive, neutral, or negative sentiment for a short text. Enter your text in the box below and press CTRl+ENTER to run the model.
+Please be patient until the demo app is loaded. """
 
-texts = st.text_area('Enter text here!')
+sentiment = pipeline("text-classification", model='tabularisai/multilingual-sentiment-analysis') #"zero-shot-classification" model='facebook/bart-large-mnli')
+
+def get_sentiment(text):
+  output = sentiment(text)
+  return f'The sentence was classified as "{output[0]["label"]}" with {output[0]["score"]*100}% confidence'
+
+demo = gr.Interface(
+    fn=get_sentiment,
+    inputs="text",
+    outputs="text",
+    title=title,
+    description=description
+)
+
+
+if __name__ == "__main__":
+    demo.launch()
+
+
+#texts = st.text_area('Enter text here!')
 #candidate_labels = ['Positive', 'Neutral', 'Negative']
-result = pipe(texts)
+#result = pipe(texts)
 
-if text:
-  out = pipe(text, result)
-  st.json(out)
-  del out
-  gc.collect()
+#if text:
+#  out = pipe(text, result)
+#  st.json(out)
+#  del out
+#  gc.collect()