Namitg02 commited on
Commit
c494c5e
·
verified ·
1 Parent(s): 55957a8

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -48,7 +48,7 @@ d = 384 # vectors dimension
48
  m = 32 # hnsw parameter. Higher is more accurate but takes more time to index (default is 32, 128 should be ok)
49
  #index = faiss.IndexHNSWFlat(d, m)
50
  index = faiss.IndexFlatL2(embedding_dim)
51
- data.add_faiss_index("embeddings", custom_index=index)
52
  # adds an index column that for the embeddings
53
 
54
  print("check1")
@@ -77,7 +77,7 @@ terminators = [
77
 
78
  def search(query: str, k: int = 3 ):
79
  """a function that embeds a new query and returns the most probable results"""
80
- embedded_query = embedding_model.encode([query]) # create embedding of a new query
81
  scores, retrieved_examples = data.get_nearest_examples( # retrieve results
82
  "embeddings", embedded_query, # compare our new embedded query with the dataset embeddings
83
  k=k # get only top k results
 
48
  m = 32 # hnsw parameter. Higher is more accurate but takes more time to index (default is 32, 128 should be ok)
49
  #index = faiss.IndexHNSWFlat(d, m)
50
  index = faiss.IndexFlatL2(embedding_dim)
51
+ data.add_faiss_index(embeddings.shape[1], custom_index=index)
52
  # adds an index column that for the embeddings
53
 
54
  print("check1")
 
77
 
78
  def search(query: str, k: int = 3 ):
79
  """a function that embeds a new query and returns the most probable results"""
80
+ embedded_query = embedding_model.encode(query) # create embedding of a new query
81
  scores, retrieved_examples = data.get_nearest_examples( # retrieve results
82
  "embeddings", embedded_query, # compare our new embedded query with the dataset embeddings
83
  k=k # get only top k results