Update streamlit_app.py

streamlit_app.py

@@ -6,6 +6,7 @@ from datetime import datetime
 import threading
 import time
 import os
+from huggingface_hub import InferenceClient
 
 # Create a global lock for file operations
 data_lock = threading.Lock()
@@ -193,9 +194,9 @@ if active_df is not None and not active_df.empty:
         st.session_state.exec_briefing = "Click the button below to generate a high-level briefing."
     st.info(st.session_state.exec_briefing)
 
-    if main.hf_client is not None:
+    if os.getenv("HF_TOKEN"):
         if st.button("Generate Briefing"):
-            with st.spinner("AI is synthesizing Radar intelligence..."):
+            with st.spinner("Gemma 31B is synthesizing your Radar intelligence..."):
                 
                 # Filter down to the Radar logic
                 temp_df = active_df[active_df['type'].isin(selected_types)] if selected_types else active_df
@@ -207,15 +208,15 @@ if active_df is not None and not active_df.empty:
                 
                 # Safe fallback in case the Radar is completely empty today
                 if briefing_items.empty:
-                    briefing_items = temp_df.head(10)
+                    briefing_items = temp_df.head(20)
                 
                 context = "\n".join([f"• SOURCE: {row['source']} | TITLE: {row['title']} | SUMMARY: {row.get('analysis', 'N/A')}" for _, row in briefing_items.iterrows()])
                 
                 # NEW: Strict context prompt
                 prompt = f"""
-                Provide a highly concise, 3-5 paragraph executive briefing based only on the recent intelligence gathered from the user's Radar tracking system.
+                Provide a highly concise, 3-5 paragraph briefing based only on the recent intelligence gathered from the user's Radar tracking system.
                 
-                Do not include outside information. Focus on legislative changes, executive actions, and tech industry shifts directly identified in the sources. Cite all sources used in the summary using in-line citations for easy user verification.
+                Do not include outside information. Cite all sources used in the summary using in-line citations for easy user verification.
 
                 Ensure you are synthesizing and summarizing information from across the Radar tracking system, not just the first 1 or 2 entries. This is a CRITICAL function for effective application funtionality.
                 All summaries should be in an understated tone. Do not infer implications or make recommendations. Simply summarize the most key information for the user.
@@ -227,11 +228,17 @@ if active_df is not None and not active_df.empty:
                 
                 messages = [{"role": "user", "content": prompt}]
                 try:
-                    response = main.hf_client.chat_completion(messages, max_tokens=500, temperature=0.2)
+                    # ---------------------------------------------------------
+                    # THE TWO-TIER ARCHITECTURE: Dedicated Gemma Client
+                    # ---------------------------------------------------------
+                    gemma_client = InferenceClient("google/gemma-4-31b-it", token=os.getenv("HF_TOKEN"))
+                    
+                    # Max tokens bumped slightly to accommodate the 3-5 paragraphs requested
+                    response = gemma_client.chat_completion(messages, max_tokens=700, temperature=0.1)
                     st.session_state.exec_briefing = response.choices[0].message.content
                     st.rerun()
                 except Exception as e: 
-                    st.error(f"Briefing failed: {e}")
+                    st.error(f"Briefing failed. (model may be loading or hitting tier limits): {e}")
 
 st.divider()