basic skeleton

app.py

@@ -1,4 +1,50 @@
 import streamlit as st
+import transformers as tf
+
+@st.experimental_singleton(show_spinner=False)
+def load_model(username, prefix, model_name):
+    p = tf.pipeline('text-classification', f'{username}/{prefix}-{model_name}')
+    return p
+
+USERNAME = 'maxspad'
+PREFIX = 'nlp-qual'
+models_to_load = ['qual', 'q1', 'q2i', 'q3i']
+n_models = float(len(models_to_load))
+
+models = {}
+
+lc_placeholder = st.empty()
+loader_container = lc_placeholder.container()
+loader_container.caption('Loading models... please wait...')
+pbar = loader_container.progress(0.0)
+for i, mn in enumerate(models_to_load):
+    pbar.progress((i+1.0) / n_models)
+    models[mn] = load_model(USERNAME, PREFIX, mn)
+lc_placeholder.empty()
+
+text = st.text_area('Type your stuff')
+
+denoms = ['5','3']
+for mn in models_to_load:
+    st.header(mn)
+    cols = st.columns(2)
+    res = models[mn](text)[0]
+
+    if mn == 'qual':
+        cols[0].metric('Score', f"{res['label'].split('_')[1]}/5")
+    elif mn == 'q1':
+        cols[0].metric('Score', f"{res['label'].split('_')[1]}/3")
+    elif mn == 'q2i':
+        if res['label'] == 'LABEL_0':
+            cols[0].metric('Suggestion for improvement?', 'Yes')
+        else:
+            cols[0].metric('Suggestion for improvement?', 'No')
+    elif mn == 'q3i':
+        if res['label'] == 'LABEL_0':
+            cols[0].metric('Suggestion linked?', 'Yes')
+        else:
+            cols[0].metric('Suggestion linked?', 'No')
+
+    cols[1].caption('Confidence')
+    cols[1].progress(res['score'])
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)