Update main.py

main.py

@@ -12,6 +12,11 @@ from pathlib import Path
 from dateutil import parser as date_parser
 from urllib.parse import urljoin
 from huggingface_hub import InferenceClient
+from sentence_transformers import SentenceTransformer
+import json
+
+# Specifying model for efficient embedding + trend analysis
+embedder = SentenceTransformer('all-MiniLM-L6-v2')
 
 # --- CONFIGURATION & GLOBALS ---
 CONGRESS_API_KEY = os.getenv("CONGRESS_API_KEY")
@@ -539,6 +544,20 @@ def run():
             
             item["analysis"] = analysis
             item["keywords"] = keywords
+            
+            # --- NEW: GENERATE SEMANTIC EMBEDDING ---
+            try:
+                # Don't waste compute embedding error messages
+                if analysis and not analysis.startswith("Error") and not analysis.startswith("AI Triage disabled"):
+                    vector = embedder.encode(analysis).tolist()
+                    item["embedding"] = json.dumps(vector) # Stored as JSON string for CSV compatibility
+                else:
+                    item["embedding"] = None
+            except Exception as e:
+                print(f"  -> Embedding error: {e}")
+                item["embedding"] = None
+            # ----------------------------------------
+            
             item["date_collected"] = datetime.now().strftime("%Y-%m-%d %H:%M")
             new_items.append(item)
             db.append(event_id)