Update app.py

app.py

@@ -8,7 +8,7 @@ import matplotlib.pyplot as plt
 from datasets import load_dataset
 from langchain_groq import ChatGroq
 from langchain_openai import ChatOpenAI
-import time  
+import time
 
 # Load environment variables
 openai_api_key = os.getenv("OPENAI_API_KEY")
@@ -33,29 +33,39 @@ def initialize_llm(model_choice):
 model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
 llm = initialize_llm(model_choice)
 
-# Cache dataset loading
-@st.cache_data
-def load_repo_dataset(file_path):
-    return pd.read_csv(file_path)
-
-@st.cache_data
-def load_huggingface_dataset(dataset_name, _progress_callback):
-    dataset = load_dataset(dataset_name, name="all", split="train", trust_remote_code=True, uniform_split=True)
-    if hasattr(dataset, "to_pandas"):
-        _progress_callback(50)  # Update progress bar
-        df = dataset.to_pandas()
-        _progress_callback(100)  # Final progress update
+# Dataset loading without caching to support progress bar
+def load_huggingface_dataset(dataset_name):
+    # Initialize progress bar
+    progress_bar = st.progress(0)
+    try:
+        # Incrementally update progress
+        progress_bar.progress(10)
+        dataset = load_dataset(dataset_name, name="all", split="train", trust_remote_code=True, uniform_split=True)
+        progress_bar.progress(50)
+        if hasattr(dataset, "to_pandas"):
+            df = dataset.to_pandas()
+        else:
+            df = pd.DataFrame(dataset)
+        progress_bar.progress(100)  # Final update to 100%
         return df
-    _progress_callback(100)
-    return pd.DataFrame(dataset)
-
-@st.cache_data
-def load_uploaded_csv(uploaded_file, _progress_callback):
-    time.sleep(1)  # Simulate processing delay
-    _progress_callback(50)  # Update progress bar
-    df = pd.read_csv(uploaded_file)
-    _progress_callback(100)  # Final progress update
-    return df
+    except Exception as e:
+        progress_bar.progress(0)  # Reset progress bar on failure
+        raise e
+
+def load_uploaded_csv(uploaded_file):
+    # Initialize progress bar
+    progress_bar = st.progress(0)
+    try:
+        # Simulate progress
+        progress_bar.progress(10)
+        time.sleep(1)  # Simulate file processing delay
+        progress_bar.progress(50)
+        df = pd.read_csv(uploaded_file)
+        progress_bar.progress(100)  # Final update
+        return df
+    except Exception as e:
+        progress_bar.progress(0)  # Reset progress bar on failure
+        raise e
 
 # Dataset selection logic
 def load_dataset_into_session():
@@ -70,7 +80,7 @@ def load_dataset_into_session():
         if st.button("Load Dataset"):
             try:
                 with st.spinner("Loading dataset from the repo directory..."):
-                    st.session_state.df = load_repo_dataset(file_path)
+                    st.session_state.df = pd.read_csv(file_path)
                 st.success(f"File loaded successfully from '{file_path}'!")
             except Exception as e:
                 st.error(f"Error loading dataset from the repo directory: {e}")
@@ -81,31 +91,21 @@ def load_dataset_into_session():
             "Enter Hugging Face Dataset Name:", value="HUPD/hupd"
         )
         if st.button("Load Dataset"):
-            progress_bar = st.progress(0)  # Initialize progress bar
-            def progress_callback(progress):
-                progress_bar.progress(progress)  # Update progress bar dynamically
-
             try:
-                st.session_state.df = load_huggingface_dataset(dataset_name, progress_callback)
+                st.session_state.df = load_huggingface_dataset(dataset_name)
                 st.success(f"Hugging Face Dataset '{dataset_name}' loaded successfully!")
             except Exception as e:
                 st.error(f"Error loading Hugging Face dataset: {e}")
-                progress_bar.progress(0)  # Reset progress bar on error
 
     # Option 3: Upload CSV File
     elif input_option == "Upload CSV File":
         uploaded_file = st.file_uploader("Upload a CSV File:", type=["csv"])
         if uploaded_file:
-            progress_bar = st.progress(0)  # Initialize progress bar
-            def progress_callback(progress):
-                progress_bar.progress(progress)  # Update progress bar dynamically
-
             try:
-                st.session_state.df = load_uploaded_csv(uploaded_file, progress_callback)
+                st.session_state.df = load_uploaded_csv(uploaded_file)
                 st.success("File uploaded successfully!")
             except Exception as e:
                 st.error(f"Error reading uploaded file: {e}")
-                progress_bar.progress(0)  # Reset progress bar on error
 
 # Load dataset into session
 load_dataset_into_session()