Skip to content

Read model from cache if offline #269

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JosephMarinier merged 2 commits into from
Oct 17, 2022
Merged

Read model from cache if offline #269

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d870e34
Read model from cache if offline
JosephMarinier Oct 14, 2022
e653d17
Clean up
JosephMarinier Oct 14, 2022
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
13 changes: 10 additions & 3 deletions azimuth/modules/dataset_analysis/similarity_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@
# This source code is licensed under the Apache 2.0 license found in the LICENSE file
# in the root directory of this source tree.
import itertools
import os
from collections import defaultdict
from os.path import join as pjoin
from typing import Dict, List, Optional, Tuple

import numpy as np
Expand Down Expand Up @@ -37,10 +37,17 @@ def __init__(
self.encoder = None
super().__init__(dataset_split_name, config, mod_options)

def get_model_name_or_path(self):
model_name_or_path = self.config.similarity.faiss_encoder
if os.environ.get("TRANSFORMERS_OFFLINE"):
home = os.environ.get("SENTENCE_TRANSFORMERS_HOME")
model_name_or_path = os.path.join(home, f"sentence-transformers_{model_name_or_path}")
return model_name_or_path

def get_model(self):
if self.encoder is None:
with FileLock(pjoin(self.cache_dir, "st.lock")):
self.encoder = SentenceTransformer(self.config.similarity.faiss_encoder)
with FileLock(os.path.join(self.cache_dir, "st.lock")):
self.encoder = SentenceTransformer(self.get_model_name_or_path())
return self.encoder

def compute_on_dataset_split(self) -> List[FAISSResponse]: # type: ignore
Expand Down