Skip to content
This repository was archived by the owner on Oct 22, 2023. It is now read-only.
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 17 additions & 1 deletion utils.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
import os
import re

import yaml
import shutil
import openai
Expand All @@ -10,6 +12,11 @@
import tensorflow_hub as hub


SUMMARIES_FOLDER_REGEX = (
r"L\d+_summaries"
)


embedding_model = hub.load("https://tfhub.dev/google/universal-sentence-encoder-large/5")


Expand Down Expand Up @@ -84,7 +91,16 @@ def search_tree(root_folder, query):
def rebuild_tree(root_folder: str, max_cluster_size: int = 10):
# Delete all folders except L1_raw_logs, L2_message_pairs and .git
for folder_name in os.listdir(root_folder):
if folder_name not in {"L1_raw_logs", "L2_message_pairs", ".git"}:

is_folder_to_delete = (
folder_name not in {"L1_raw_logs", "L2_message_pairs", ".git"}
and re.match(
SUMMARIES_FOLDER_REGEX,
folder_name,
)
)

if is_folder_to_delete:
folder_path = os.path.join(root_folder, folder_name)
if os.path.isdir(folder_path):
shutil.rmtree(folder_path)
Expand Down