feat: make embedding model configurable for semantic search

- Add SemanticSearchConfig to settings.py with embedding model options
- Update WorldMapper to accept embedding_model parameter
- Update main.py to pass model from config to WorldMapper
- Add documentation for available embedding models:
  - sentence-transformers/all-MiniLM-L6-v2 (default, fast)
  - sentence-transformers/all-mpnet-base-v2 (better quality)
  - google/embeddinggemma-300m (state-of-the-art)
- Update config.yaml and config.example.yaml with new options

Users can now choose the best embedding model for their needs.

src/config/settings.py

@@ -51,24 +51,30 @@ class AIConfig(BaseModel):
     llm: LLMProviderConfig = Field(default_factory=LLMProviderConfig)
 
 
-class MapperConfig(BaseModel):
-    """Mapper configuration"""
-    class ActiveStorageConfig(BaseModel):
-        db_path: str = "data/maps/active/world.db"
-        graph_cache_size: int = 10000
-    
-    class HistoricalStorageConfig(BaseModel):
-        archive_dir: str = "data/maps/archive"
-        
-        class SnapshotTriggers(BaseModel):
-            room_count: int = 500
-            session_end: bool = True
-            time_interval_hours: int = 24
-        
-        snapshot_triggers: SnapshotTriggers = Field(default_factory=SnapshotTriggers)
-    
-    active_storage: ActiveStorageConfig = Field(default_factory=ActiveStorageConfig)
-    historical_storage: HistoricalStorageConfig = Field(default_factory=HistoricalStorageConfig)
+class MapperConfig(BaseModel):
+    """Mapper configuration"""
+    class ActiveStorageConfig(BaseModel):
+        db_path: str = "data/maps/active/world.db"
+        graph_cache_size: int = 10000
+    
+    class HistoricalStorageConfig(BaseModel):
+        archive_dir: str = "data/maps/archive"
+        
+        class SnapshotTriggers(BaseModel):
+            room_count: int = 500
+            session_end: bool = True
+            time_interval_hours: int = 24
+        
+        snapshot_triggers: SnapshotTriggers = Field(default_factory=SnapshotTriggers)
+    
+    class SemanticSearchConfig(BaseModel):
+        model: str = "sentence-transformers/all-MiniLM-L6-v2"
+        top_k: int = 5
+        similarity_threshold: float = 0.7
+    
+    active_storage: ActiveStorageConfig = Field(default_factory=ActiveStorageConfig)
+    historical_storage: HistoricalStorageConfig = Field(default_factory=HistoricalStorageConfig)
+    semantic_search: SemanticSearchConfig = Field(default_factory=SemanticSearchConfig)
 
 
 class BehaviorConfig(BaseModel):