Update app.py

app.py

@@ -14,7 +14,6 @@ from transformers import AutoTokenizer
 from transformers import AutoModelForCausalLM
 from transformers import TextIteratorStreamer
 from threading import Thread
-from langchain import Dimension
 
 
 
@@ -43,9 +42,10 @@ embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
 data = dataset["train"]
 
 print(data)
-d = 384
-faiss = faiss.IndexFlatL2(d)
-data = data.add_faiss_index("embeddings") 
+d = 384  # vectors dimension
+m = 32  # hnsw parameter. Higher is more accurate but takes more time to index (default is 32, 128 should be ok)
+index = faiss.IndexHNSWFlat(d, m, faiss.METRIC_INNER_PRODUCT)
+data = data.add_faiss_index("embeddings", custom_index=index) 
 # adds an index column that for the embeddings