a int8 -> an int8

app.py

@@ -82,7 +82,7 @@ Details:
 1. The query is embedded using the [`mixedbread-ai/mxbai-embed-large-v1`](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) SentenceTransformer model.
 2. The query is quantized to binary using the `quantize_embeddings` function from the SentenceTransformers library.
 3. A binary index (1M binary embeddings; 130MB of memory/disk space) is searched using the quantized query for the top 40 documents.
-4. The top 40 documents are loaded on the fly from a int8 index on disk (1M int8 embeddings; 0 bytes of memory, 1.19GB of disk space).
+4. The top 40 documents are loaded on the fly from an int8 index on disk (1M int8 embeddings; 0 bytes of memory, 1.19GB of disk space).
 5. The top 40 documents are rescored using the float32 query and the int8 embeddings to get the top 10 documents.
 6. The top 10 documents are sorted by score and displayed.