Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,13 +1,12 @@
 # streamlit_data_analysis_app.py
-# Streamlit Data Analysis App for Hugging Face Spaces + Gemini 2.0 Flash
+# Streamlit Data Analysis App using Gemini 2.0 Flash (Free-tier)
 # Features:
 # - Upload CSV / Excel
 # - Automatic cleaning & standardization
 # - Preprocessing (imputation, encoding, scaling)
 # - Quick visualizations
 # - Dataset summary + preview
-# - Insights from LLMs (Gemini or Hugging Face)
-# - Auto fallback and detailed error messages
+# - Insights powered by Gemini 2.0 Flash (Google AI)
 
 import os
 import streamlit as st
@@ -19,49 +18,36 @@ from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, StandardScaler
 from sklearn.compose import ColumnTransformer
 from sklearn.pipeline import Pipeline
-from huggingface_hub import InferenceClient
 import google.generativeai as genai
 
 # ---------- CONFIGURATION ----------
 st.set_page_config(page_title="Data Analysis App", layout="wide")
 
-# Load API keys safely
-try:
-    HF_TOKEN = st.secrets["HF_TOKEN"]
-except Exception:
-    HF_TOKEN = os.getenv("HF_TOKEN")
-
+# Load Gemini API key safely
 try:
     GEMINI_API_KEY = st.secrets["GEMINI_API_KEY"]
 except Exception:
     GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
 
-# Setup Gemini if available
 if GEMINI_API_KEY:
     genai.configure(api_key=GEMINI_API_KEY)
     st.success("✅ Gemini API key loaded successfully.")
-elif HF_TOKEN:
-    st.success("✅ Hugging Face token loaded successfully.")
 else:
-    st.warning("⚠️ No Gemini or Hugging Face token found. LLM features will be disabled.")
-
-# Default models
-MODEL_OPTIONS = {
-    "gemini-2.0-flash": "Gemini 2.0 Flash (Google AI, fast, free-tier)",
-    "mistralai/Mistral-7B-Instruct-v0.3": "Mistral 7B Instruct (open)",
-    "HuggingFaceH4/zephyr-7b-beta": "Zephyr 7B Beta (open)",
-    "bigscience/bloom-3b": "Bloom 3B (lightweight)",
-}
+    st.warning("⚠️ No Gemini API key found. Please add GEMINI_API_KEY to .env or Streamlit secrets.")
 
 # ---------- UTILITIES ----------
 def read_file(uploaded_file):
     name = uploaded_file.name.lower()
-    if name.endswith(('.csv', '.txt')):
-        return pd.read_csv(uploaded_file)
-    elif name.endswith(('.xls', '.xlsx')):
-        return pd.read_excel(uploaded_file)
-    else:
-        raise ValueError("Unsupported file type. Please upload CSV or Excel.")
+    try:
+        if name.endswith(('.csv', '.txt')):
+            return pd.read_csv(uploaded_file, encoding="utf-8", errors="replace")
+        elif name.endswith(('.xls', '.xlsx')):
+            return pd.read_excel(uploaded_file)
+        else:
+            raise ValueError("Unsupported file type. Please upload CSV or Excel.")
+    except Exception as e:
+        st.error(f"❌ File reading failed: {e}")
+        raise
 
 def clean_column_name(col: str) -> str:
     col = str(col).strip().lower().replace("\n", " ").replace("\t", " ")
@@ -138,7 +124,7 @@ def apply_preprocessing(df: pd.DataFrame, preprocessor: ColumnTransformer) -> pd
                 feature_names += cols
     return pd.DataFrame(X, columns=feature_names)
 
-# ---------- LLM HELPERS ----------
+# ---------- LLM (Gemini only) ----------
 def build_dataset_prompt(summary, user_question=None):
     s = [f"Dataset shape: {summary['shape'][0]} rows, {summary['shape'][1]} columns."]
     for c in summary['columns']:
@@ -152,31 +138,7 @@ def build_dataset_prompt(summary, user_question=None):
         s.append("Please provide a summary, notable patterns, and suggestions for visualizations.")
     return "\n".join(s)
 
-def call_llm_huggingface(prompt: str, model: str, max_tokens: int = 512) -> str:
-    if not HF_TOKEN:
-        return "⚠️ No Hugging Face token found."
-    client = InferenceClient(token=HF_TOKEN)
-    try:
-        response = client.text_generation(model=model, inputs=prompt, max_new_tokens=max_tokens)
-        if isinstance(response, dict):
-            return response.get('generated_text', str(response))
-        return str(response)
-    except Exception as e:
-        if "403" in str(e):
-            fallback = "mistralai/Mistral-7B-Instruct-v0.3"
-            if model != fallback:
-                try:
-                    st.warning(f"🚫 Access denied to {model}. Falling back to {fallback}...")
-                    response = client.text_generation(model=fallback, inputs=prompt, max_new_tokens=max_tokens)
-                    if isinstance(response, dict):
-                        return response.get('generated_text', str(response))
-                    return str(response)
-                except Exception as e2:
-                    return f"❌ Fallback model also failed: {e2}"
-            return "🚫 Access denied (403). Try using an open-access model."
-        return f"❌ LLM call failed: {e}"
-
-def call_llm_gemini(prompt: str, model="gemini-2.0-flash", max_tokens=512):
+def call_llm_gemini(prompt: str, model="gemini-2.0-flash"):
     if not GEMINI_API_KEY:
         return "⚠️ Gemini API key not found."
     try:
@@ -187,13 +149,12 @@ def call_llm_gemini(prompt: str, model="gemini-2.0-flash", max_tokens=512):
         return f"❌ Gemini call failed: {e}"
 
 # ---------- STREAMLIT UI ----------
-st.title("📊 Data Analysis & Cleaning App")
-st.markdown("Upload CSV or Excel, clean and preprocess it, visualize data, and get insights from an AI model.")
+st.title("📊 Data Analysis & Cleaning App (Gemini-Powered)")
+st.markdown("Upload CSV or Excel, clean and preprocess it, visualize data, and get insights powered by **Gemini 2.0 Flash**.")
 
 with st.sidebar:
     st.header("⚙️ Options")
-    model_choice = st.selectbox("Select Model", options=list(MODEL_OPTIONS.keys()), format_func=lambda k: MODEL_OPTIONS[k])
-    max_tokens = st.slider("LLM max tokens", 128, 1024, 512, 64)
+    st.info("Using **Gemini 2.0 Flash (Google AI)** for insights.")
     impute_strategy_num = st.selectbox("Numeric imputation", ['mean', 'median', 'most_frequent'])
     encode_categorical = st.selectbox("Categorical encoding", ['onehot', 'ordinal'])
     scale_numeric = st.checkbox("Scale numeric features", True)
@@ -235,7 +196,7 @@ if uploaded_file:
         second_col = st.selectbox("Second column", options=[c for c in cleaned_df.columns if c != viz_col])
 
     if st.button("Show Visualization"):
-        fig, ax = plt.subplots(figsize=(8,5))
+        fig, ax = plt.subplots(figsize=(8, 5))
         try:
             if viz_type == 'Histogram':
                 sns.histplot(cleaned_df[viz_col], kde=True, ax=ax)
@@ -253,15 +214,12 @@ if uploaded_file:
         except Exception as e:
             st.error(f"Visualization failed: {e}")
 
-    st.subheader("🧠 Ask the AI for Insights")
+    st.subheader("🧠 Ask Gemini for Insights")
     user_q = st.text_area("Enter your question (optional):")
     if st.button("Get Insights"):
-        with st.spinner("Generating insights..."):
+        with st.spinner("Generating insights via Gemini..."):
             prompt = build_dataset_prompt(summary, user_q if user_q else None)
-            if model_choice.startswith("gemini"):
-                llm_resp = call_llm_gemini(prompt, model_choice, max_tokens)
-            else:
-                llm_resp = call_llm_huggingface(prompt, model_choice, max_tokens)
+            llm_resp = call_llm_gemini(prompt)
             st.write(llm_resp)
 
 else: