ss

app.py

@@ -38,12 +38,6 @@ st.set_page_config(
 with st.sidebar:
     st.title("⚙️ Configuration")
     
-    # Ranking weights
-    st.subheader("Ranking Weights")
-    semantic_weight = st.slider("Semantic Similarity Weight", 0.0, 1.0, 0.7, 0.1)
-    keyword_weight = 1.0 - semantic_weight
-    st.write(f"Keyword Weight: {keyword_weight:.1f}")
-    
     # Advanced options
     st.subheader("Advanced Options")
     top_k = st.selectbox("Number of results to display", [1,2,3,4,5], index=4)
@@ -98,8 +92,10 @@ def load_embedding_model():
     """Load and cache the BGE embedding model"""
     print("[Cache] Attempting to load Embedding Model (BAAI/bge-large-en-v1.5)...")
     try:
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        print(f"[Cache] Using device: {device} for embedding model")
         with st.spinner("🔄 Loading BAAI/bge-large-en-v1.5 model..."):
-            model = SentenceTransformer('BAAI/bge-large-en-v1.5')
+            model = SentenceTransformer('BAAI/bge-large-en-v1.5', device=device)
             st.success("✅ Embedding model loaded successfully!")
             print("[Cache] Embedding Model (BAAI/bge-large-en-v1.5) LOADED.")
             return model
@@ -112,9 +108,11 @@ def load_cross_encoder():
     """Load and cache the Cross-Encoder model"""
     print("[Cache] Attempting to load Cross-Encoder Model (ms-marco-MiniLM-L6-v2)...")
     try:
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        print(f"[Cache] Using device: {device} for cross-encoder model")
         with st.spinner("🔄 Loading Cross-Encoder ms-marco-MiniLM-L6-v2..."):
             from sentence_transformers import CrossEncoder
-            model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L6-v2')
+            model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L6-v2', device=device)
             st.success("✅ Cross-Encoder model loaded successfully!")
             print("[Cache] Cross-Encoder Model (ms-marco-MiniLM-L6-v2) LOADED.")
             return model

requirements.txt

@@ -14,6 +14,6 @@ huggingface-hub==0.30.0
 bitsandbytes==0.44.1
 accelerate==0.27.2
 datasets==2.18.0
-sentence-transformers==2.7.0
+sentence-transformers>=3.0.0,<4.0.0
 plotly==5.18.0
 einops