MOD: batch size

retriever/embedder.py

@@ -12,7 +12,7 @@ class Embedder:
         self.model = SentenceTransformer(model_name, device=device)
         logger.info(f"Loaded embedding model: {model_name}")
     
-    def encode(self, texts: Union[str, List[str]], batch_size: int = 32) -> np.ndarray:
+    def encode(self, texts: Union[str, List[str]], batch_size: int = 16) -> np.ndarray:
         """Encode texts to embeddings"""
         if isinstance(texts, str):
             texts = [texts]
@@ -26,7 +26,7 @@ class Embedder:
         
         return embeddings
     
-    def encode_queries(self, queries: List[str], batch_size: int = 32) -> np.ndarray:
+    def encode_queries(self, queries: List[str], batch_size: int = 16) -> np.ndarray:
         """Encode queries with query prefix"""
         if not queries:
             return np.array([])
@@ -35,7 +35,7 @@ class Embedder:
         prefixed_queries = [f"Represent this sentence for searching relevant passages: {q}" for q in queries]
         return self.encode(prefixed_queries, batch_size)
     
-    def encode_passages(self, passages: List[str], batch_size: int = 32) -> np.ndarray:
+    def encode_passages(self, passages: List[str], batch_size: int = 16) -> np.ndarray:
         """Encode passages with passage prefix"""
         if not passages:
             return np.array([])