zstanjj commited on
Commit
5b0bdbe
1 Parent(s): 0a40430

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -152,6 +152,21 @@ print(block_rankings)
152
 
153
  # [1, 0]
154
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  max_context_window = 32
156
  pruned_html = gen_embed_pruner.prune_HTML(pruned_html, block_tree, block_rankings, chat_tokenizer, max_context_window)
157
  print(pruned_html)
 
152
 
153
  # [1, 0]
154
 
155
+ block_tree, pruned_html=build_block_tree(pruned_html, max_node_words=10)
156
+ for block in block_tree:
157
+ print("Block Content: ", block[0])
158
+ print("Block Path: ", block[1])
159
+ print("Is Leaf: ", block[2])
160
+ print("")
161
+
162
+ # Block Content: <title>When was the bellagio in las vegas built?</title>
163
+ # Block Path: ['html', 'title']
164
+ # Is Leaf: True
165
+ #
166
+ # Block Content: <p>The Bellagio is a luxury hotel and casino located on the Las Vegas Strip in Paradise, Nevada. It was built in 1998.</p>
167
+ # Block Path: ['html', 'p']
168
+ # Is Leaf: True
169
+
170
  max_context_window = 32
171
  pruned_html = gen_embed_pruner.prune_HTML(pruned_html, block_tree, block_rankings, chat_tokenizer, max_context_window)
172
  print(pruned_html)