Update src/app.py

src/app.py

@@ -1,27 +1,22 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
-import re
 import os
-
+import faiss
+import nltk
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sentence_transformers import SentenceTransformer
 from rank_bm25 import BM25Okapi
-from rapidfuzz import fuzz
-import faiss
-import nltk
 
 # ==============================
-# NLTK FIX
+# INITIALIZATION & NLTK
 # ==============================
 nltk.download('wordnet', quiet=True)
-from nltk.corpus import wordnet
+LOG_FILE = "user_logs.csv"
 
 # ==============================
-# LOG FUNCTION (FIXED POSITION)
+# LOGGING UTILITY
 # ==============================
-LOG_FILE = "user_logs.csv"
-
 def log_activity(user, action, query, search_type):
     log_entry = {
         "User": user,
@@ -30,48 +25,43 @@ def log_activity(user, action, query, search_type):
         "Search Type": search_type,
         "Time": str(pd.Timestamp.now())
     }
-
-    if os.path.exists(LOG_FILE):
-        df_log = pd.read_csv(LOG_FILE)
-        df_log = pd.concat([df_log, pd.DataFrame([log_entry])])
-    else:
-        df_log = pd.DataFrame([log_entry])
-
-    df_log.to_csv(LOG_FILE, index=False)
+    try:
+        if os.path.exists(LOG_FILE):
+            df_log = pd.read_csv(LOG_FILE)
+            df_log = pd.concat([df_log, pd.DataFrame([log_entry])], ignore_index=True)
+        else:
+            df_log = pd.DataFrame([log_entry])
+        df_log.to_csv(LOG_FILE, index=False)
+    except Exception:
+        pass # Prevent app crash on logging errors
 
 # ==============================
-# AUTHENTICATION
+# SECRETS & AUTHENTICATION
 # ==============================
 def login():
     st.title("🔐 Login Required")
+    
+    # Hugging Face exposes secrets as environment variables
+    # We check both os.environ (Cloud) and st.secrets (Local)
+    HF_USER = os.environ.get("USERNAME") or st.secrets.get("USERNAME")
+    HF_PASS = os.environ.get("PASSWORD") or st.secrets.get("PASSWORD")
 
     username = st.text_input("Username")
     password = st.text_input("Password", type="password")
 
     if st.button("Login"):
-        try:
-            if (
-                username == st.secrets["USERNAME"] and
-                password == st.secrets["PASSWORD"]
-            ):
-                st.session_state["authenticated"] = True
-                st.session_state["user"] = username
-                st.session_state["login_time"] = pd.Timestamp.now()
-
-                log_activity(username, "Login Success", "-", "-")
-
-                st.success("✅ Login successful")
-                st.rerun()
-            else:
-                log_activity(username, "Login Failed", "-", "-")
-                st.error("❌ Invalid credentials")
-
-        except Exception:
-            st.error("⚠️ Secrets not configured properly")
+        if not HF_USER or not HF_PASS:
+            st.error("⚠️ Secrets not configured! Add USERNAME and PASSWORD in Hugging Face Settings.")
+        elif username == HF_USER and password == HF_PASS:
+            st.session_state["authenticated"] = True
+            st.session_state["user"] = username
+            st.session_state["login_time"] = pd.Timestamp.now()
+            log_activity(username, "Login Success", "-", "-")
+            st.rerun()
+        else:
+            log_activity(username, "Login Failed", "-", "-")
+            st.error("❌ Invalid credentials")
 
-# ==============================
-# SESSION CONTROL
-# ==============================
 if "authenticated" not in st.session_state:
     st.session_state["authenticated"] = False
 
@@ -80,124 +70,108 @@ if not st.session_state["authenticated"]:
     st.stop()
 
 # ==============================
-# PAGE CONFIG
+# PAGE CONFIG & UI
 # ==============================
 st.set_page_config(page_title="Multi Search Engine", layout="wide")
 st.title("🔍 Advanced Multi-Search Product Engine")
 
-# Sidebar info
 st.sidebar.success(f"👤 User: {st.session_state['user']}")
-st.sidebar.info(f"🕒 Login: {st.session_state['login_time']}")
-
-# Logout button
 if st.sidebar.button("🚪 Logout"):
     log_activity(st.session_state["user"], "Logout", "-", "-")
     st.session_state.clear()
     st.rerun()
 
 # ==============================
-# LOAD MODEL
+# DATA LOADING & CACHING
 # ==============================
 @st.cache_resource
 def load_model():
     return SentenceTransformer('all-MiniLM-L6-v2', device='cpu')
 
-model = load_model()
+@st.cache_data
+def load_data():
+    path = "src/products_10k.csv"
+    if not os.path.exists(path):
+        st.error(f"Missing data file at {path}")
+        return None
+    df = pd.read_csv(path)
+    # Fill NaN values to prevent search errors
+    df["combined"] = (
+        df["product_name"].fillna("") + " " +
+        df["category"].fillna("") + " " +
+        df["brand"].fillna("") + " " +
+        df["description"].fillna("")
+    )
+    return df
 
-# ==============================
-# LOAD DATA
-# ==============================
-try:
-    df = pd.read_csv("src/products_10k.csv")
-    st.success("✅ Data loaded successfully (10K Products)")
-except Exception as e:
-    st.error(f"❌ Error loading file: {e}")
-    st.stop()
+model = load_model()
+df = load_data()
+if df is None: st.stop()
 
 # ==============================
-# PREPROCESS
+# SEARCH PRE-PROCESSING
 # ==============================
-df["combined"] = (
-    df["product_name"].astype(str) + " " +
-    df["category"].astype(str) + " " +
-    df["brand"].astype(str) + " " +
-    df["description"].astype(str)
-)
-
-products = df["combined"].tolist()
-
 @st.cache_resource
-def preprocess_data(products):
+def get_search_assets(products):
+    # TF-IDF
     tfidf = TfidfVectorizer()
     tfidf_matrix = tfidf.fit_transform(products)
-
+    
+    # Semantic/FAISS
     embeddings = model.encode(products, show_progress_bar=False)
     faiss.normalize_L2(embeddings)
-
     index = faiss.IndexFlatIP(embeddings.shape[1])
     index.add(np.array(embeddings))
-
-    tokenized = [p.split() for p in products]
+    
+    # BM25
+    tokenized = [p.lower().split() for p in products]
     bm25 = BM25Okapi(tokenized)
-
+    
     return tfidf, tfidf_matrix, embeddings, index, bm25
 
-tfidf, tfidf_matrix, embeddings, index, bm25 = preprocess_data(products)
+products_list = df["combined"].tolist()
+tfidf, tf_matrix, embs, faiss_index, bm25 = get_search_assets(products_list)
 
 # ==============================
 # SEARCH FUNCTIONS
 # ==============================
-def keyword_search(q):
-    return [(i, 1) for i, p in enumerate(products) if q.lower() in p.lower()]
-
-def semantic_search(q):
-    q_emb = model.encode([q])
-    faiss.normalize_L2(q_emb)
-    scores = np.dot(embeddings, q_emb.T).flatten()
-    return list(enumerate(scores))
+def run_search(q, mode, k):
+    if mode == "Keyword":
+        # Simple boolean check for exact matches
+        matches = [(i, 1.0) for i, p in enumerate(products_list) if q.lower() in p.lower()]
+        return matches[:k]
+    else:
+        # Semantic search using FAISS
+        q_emb = model.encode([q])
+        faiss.normalize_L2(q_emb)
+        scores, indices = faiss_index.search(np.array(q_emb), k)
+        return list(zip(indices[0], scores[0]))
 
 # ==============================
-# UI
+# MAIN APP EXECUTION
 # ==============================
 search_type = st.selectbox("🔎 Search Type", ["Keyword", "Semantic"])
-query = st.text_input("Enter your search query")
-top_k = st.slider("Top Results", 5, 20, 10)
-
-# ==============================
-# SEARCH
-# ==============================
-if st.button("Search"):
-    if not query:
-        st.warning("Enter query")
+query = st.text_input("Search for products...")
+top_k = st.slider("Results to show", 5, 50, 10)
+
+if st.button("Search") and query:
+    results = run_search(query, search_type, top_k)
+    log_activity(st.session_state["user"], "Search", query, search_type)
+
+    if results:
+        idx = [r[0] for r in results if r[0] != -1]
+        scores = [r[1] for r in results if r[0] != -1]
+        
+        final_df = df.iloc[idx].copy()
+        final_df["Match Score"] = scores
+        st.dataframe(final_df.drop(columns=["combined"]), use_container_width=True)
     else:
-        if search_type == "Keyword":
-            results = keyword_search(query)
-        else:
-            results = semantic_search(query)
-
-        results = sorted(results, key=lambda x: x[1], reverse=True)[:top_k]
-
-        # ✅ LOG SEARCH
-        log_activity(
-            st.session_state["user"],
-            "Search",
-            query,
-            search_type
-        )
-
-        indices = [i for i, _ in results]
-        result_df = df.iloc[indices].copy()
-        result_df["Score"] = [round(score, 4) for _, score in results]
-
-        st.dataframe(result_df)
+        st.info("No matching products found.")
 
 # ==============================
-# VIEW LOGS
+# SIDEBAR LOGS
 # ==============================
-st.sidebar.subheader("📊 User Logs")
-
+st.sidebar.markdown("---")
+st.sidebar.subheader("📊 Recent Activity")
 if os.path.exists(LOG_FILE):
-    log_df = pd.read_csv(LOG_FILE)
-    st.sidebar.dataframe(log_df.tail(10))
-else:
-    st.sidebar.write("No logs yet")
+    st.sidebar.dataframe(pd.read_csv(LOG_FILE).tail(5))