martina3435 commited on
Commit
b4eefb5
·
verified ·
1 Parent(s): 7df2e0f

Update generate_embeddings.py

Browse files
Files changed (1) hide show
  1. generate_embeddings.py +2 -2
generate_embeddings.py CHANGED
@@ -26,8 +26,8 @@ def load_pdfs(folder_path):
26
 
27
  def split_documents(docs):
28
  text_splitter = RecursiveCharacterTextSplitter(
29
- chunk_size=500,
30
- chunk_overlap=50
31
  )
32
  chunks = text_splitter.split_documents(docs)
33
  print(f"Total chunks: {len(chunks)}")
 
26
 
27
  def split_documents(docs):
28
  text_splitter = RecursiveCharacterTextSplitter(
29
+ chunk_size=700,
30
+ chunk_overlap=100
31
  )
32
  chunks = text_splitter.split_documents(docs)
33
  print(f"Total chunks: {len(chunks)}")