Update src/streamlit_app.py

src/streamlit_app.py

@@ -51,6 +51,19 @@ EMBEDDING_MODELS = {
     }
 }
 
+# ============================================================================
+# INITIALIZE SESSION STATE - MUST BE BEFORE ANY st.session_state ACCESS
+# ============================================================================
+
+if 'processing_complete' not in st.session_state:
+    st.session_state.processing_complete = False
+if 'last_processed_files' not in st.session_state:
+    st.session_state.last_processed_files = []
+if 'processing_stats' not in st.session_state:
+    st.session_state.processing_stats = {}
+if 'embedding_model' not in st.session_state:
+    st.session_state.embedding_model = EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"]
+
 # ============================================================================
 # CACHED RESOURCES
 # ============================================================================
@@ -256,17 +269,6 @@ def get_vector_count(qdrant):
     except:
         return 0
 
-# ============================================================================
-# INITIALIZE SESSION STATE
-# ============================================================================
-
-if 'processing_complete' not in st.session_state:
-    st.session_state.processing_complete = False
-if 'last_processed_files' not in st.session_state:
-    st.session_state.last_processed_files = []
-if 'processing_stats' not in st.session_state:
-    st.session_state.processing_stats = {}
-
 # ============================================================================
 # INITIALIZE
 # ============================================================================
@@ -293,7 +295,7 @@ try:
     
     # Get current embedding model
     current_model_key = None
-    current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+    current_model_name = st.session_state.embedding_model
     for key, value in EMBEDDING_MODELS.items():
         if value["name"] == current_model_name:
             current_model_key = key
@@ -371,7 +373,7 @@ with tab1:
         st.subheader("Embedding Model")
         
         # Get current model
-        current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+        current_model_name = st.session_state.embedding_model
         current_model_key = None
         for key, value in EMBEDDING_MODELS.items():
             if value["name"] == current_model_name:
@@ -397,7 +399,7 @@ with tab1:
 - **Quality:** {model_info['quality']}
         """)
         
-        # Update session state
+        # Update session state only if different
         if st.session_state.embedding_model != model_info['name']:
             if st.button("🔄 Apply Model Change"):
                 st.session_state.embedding_model = model_info['name']
@@ -523,7 +525,7 @@ with tab1:
                         total_est_words = est_words * len(selected_files)
                         
                         # Get embedding dimensions
-                        current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+                        current_model_name = st.session_state.embedding_model
                         dimensions = 384  # default
                         for key, value in EMBEDDING_MODELS.items():
                             if value["name"] == current_model_name:
@@ -551,7 +553,7 @@ with tab1:
                 # Process button
                 if st.button("🚀 PROCESS SELECTED FILES", type="primary", key="process_button"):
                     
-                    current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+                    current_model_name = st.session_state.embedding_model
                     embedder = get_embedding_model(current_model_name)
                     
                     context_books = ""
@@ -735,7 +737,7 @@ with tab1:
                 try:
                     from datasets import load_dataset
                     
-                    current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+                    current_model_name = st.session_state.embedding_model
                     embedder = get_embedding_model(current_model_name)
                     
                     with st.spinner(f"Loading {dataset_name}..."):
@@ -798,7 +800,7 @@ with tab2:
     
     if st.button("🚀 SOLVE", type="primary", key="solve_button") and problem:
         
-        current_model_name = st.session_state.get('embedding_model', EMBEDDING_MODELS["MiniLM-L6 (Fast, 384D)"]["name"])
+        current_model_name = st.session_state.embedding_model
         embedder = get_embedding_model(current_model_name)
         
         with st.spinner("Searching knowledge base..."):