diff --git a/examples/test_faiss.py b/examples/test_faiss.py
index e73c0bfc..ab0ef9f7 100644
--- a/examples/test_faiss.py
+++ b/examples/test_faiss.py
@@ -8,7 +8,6 @@ from sentence_transformers import SentenceTransformer
 from openai import AzureOpenAI
 from lightrag import LightRAG, QueryParam
 from lightrag.utils import EmbeddingFunc
-from lightrag.kg.faiss_impl import FaissVectorDBStorage
 
 # Configure Logging
 logging.basicConfig(level=logging.INFO)
@@ -20,14 +19,10 @@ AZURE_OPENAI_DEPLOYMENT = os.getenv("AZURE_OPENAI_DEPLOYMENT")
 AZURE_OPENAI_API_KEY = os.getenv("AZURE_OPENAI_API_KEY")
 AZURE_OPENAI_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT")
 
+
 async def llm_model_func(
-    prompt,
-    system_prompt=None,
-    history_messages=[],
-    keyword_extraction=False,
-    **kwargs
+    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> str:
-    
     # Create a client for AzureOpenAI
     client = AzureOpenAI(
         api_key=AZURE_OPENAI_API_KEY,
@@ -56,12 +51,12 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    model = SentenceTransformer('all-MiniLM-L6-v2')
+    model = SentenceTransformer("all-MiniLM-L6-v2")
     embeddings = model.encode(texts, convert_to_numpy=True)
     return embeddings
 
+
 def main():
-    
     WORKING_DIR = "./dickens"
 
     # Initialize LightRAG with the LLM model function and embedding function
@@ -76,7 +71,7 @@ def main():
         vector_storage="FaissVectorDBStorage",
         vector_db_storage_cls_kwargs={
             "cosine_better_than_threshold": 0.3  # Your desired threshold
-        }
+        },
     )
 
     # Insert the custom chunks into LightRAG
@@ -101,4 +96,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()
diff --git a/lightrag/kg/faiss_impl.py b/lightrag/kg/faiss_impl.py
index 1688e507..fc6aa779 100644
--- a/lightrag/kg/faiss_impl.py
+++ b/lightrag/kg/faiss_impl.py
@@ -22,6 +22,7 @@ class FaissVectorDBStorage(BaseVectorStorage):
     A Faiss-based Vector DB Storage for LightRAG.
     Uses cosine similarity by storing normalized vectors in a Faiss index with inner product search.
     """
+
     cosine_better_than_threshold: float = float(os.getenv("COSINE_THRESHOLD", "0.2"))
 
     def __post_init__(self):
@@ -46,7 +47,7 @@ class FaissVectorDBStorage(BaseVectorStorage):
         # For demonstration, we use a simple IndexFlatIP.
         self._index = faiss.IndexFlatIP(self._dim)
 
-        # Keep a local store for metadata, IDs, etc. 
+        # Keep a local store for metadata, IDs, etc.
         # Maps <int faiss_id> → metadata (including your original ID).
         self._id_to_meta = {}
 
@@ -93,7 +94,9 @@ class FaissVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        pbar = tqdm_async(total=len(batches), desc="Generating embeddings", unit="batch")
+        pbar = tqdm_async(
+            total=len(batches), desc="Generating embeddings", unit="batch"
+        )
 
         async def wrapped_task(batch):
             result = await self.embedding_func(batch)
@@ -200,7 +203,9 @@ class FaissVectorDBStorage(BaseVectorStorage):
 
         if to_remove:
             self._remove_faiss_ids(to_remove)
-        logger.info(f"Successfully deleted {len(to_remove)} vectors from {self.namespace}")
+        logger.info(
+            f"Successfully deleted {len(to_remove)} vectors from {self.namespace}"
+        )
 
     async def delete_entity(self, entity_name: str):
         """
@@ -288,7 +293,7 @@ class FaissVectorDBStorage(BaseVectorStorage):
 
     def _load_faiss_index(self):
         """
-        Load the Faiss index + metadata from disk if it exists, 
+        Load the Faiss index + metadata from disk if it exists,
         and rebuild in-memory structures so we can query.
         """
         if not os.path.exists(self._faiss_index_file):