HF_inference.py

@@ -69,7 +69,7 @@ headers = {"Authorization": SECRET_TOKEN}
 MAX_RETRIES = 3
 RETRY_INTERVAL = 1  # in seconds
 
-@st.cache_resource(experimental_allow_widgets=True, show_spinner=False)
+# @st.cache_resource(experimental_allow_widgets=True, show_spinner=False)
 def query(payload, selected_model):
     # st.write(selected_model)
     
@@ -81,7 +81,7 @@ def query(payload, selected_model):
         if response.status_code == 200:
             return response.json()
         else:
-            st.info("loadings")
+            st.info("loading..")
             time.sleep(RETRY_INTERVAL)
 
     return None

HF_pipeline.py

@@ -0,0 +1,19 @@
+from transformers import pipeline
+import streamlit as st
+
+MODEL_URLS = {
+    "DISTILIBERT MODEL": "MENG21/stud-fac-eval-distilbert-base-uncased",
+    "BERT-LARGE MODEL": "MENG21/stud-fac-eval-bert-large-uncased",
+    "BERT-BASE MODEL": "MENG21/stud-fac-eval-bert-base-uncased"
+}
+
+@st.cache_resource(experimental_allow_widgets=True, show_spinner=False)
+def analyze_sintement(text, selected_model):
+    # st.write(selected_model)
+    
+    # API_URL = MODEL_URLS.get(selected_model, MODEL_URLS[selected_model])  # Get API URL based on selected model
+    # Create a text classification pipeline
+    classifier = pipeline("text-classification", model=MODEL_URLS[selected_model])
+
+    result = classifier(text)
+    return result

app5_selectbox/evaluation_analysis.py

@@ -19,7 +19,9 @@ from app5_selectbox.g4f_prompt import g4f_prompt
 # from app5_selectbox.llama2_prompt import llama_prompt
 from app5_selectbox.naive_bayes_cl import nb_clf
 
-from HF_inference import analyze_sintement
+# from HF_inference import analyze_sintement
+
+from HF_pipeline import analyze_sintement
 
 models = ['BERT-BASE MODEL', 'BERT-LARGE MODEL', 'DISTILIBERT MODEL', 'NAIVE BAYES MODEL']