mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 12:32:30 +08:00
Updated Dockefile to use cache (#2703)
### What problem does this PR solve? Updated Dockefile to use cache ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [ ] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [x] Other (please describe): CI
This commit is contained in:
@ -1,6 +1,7 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
from huggingface_hub import snapshot_download
|
||||
import nltk
|
||||
import os
|
||||
|
||||
repos = [
|
||||
@ -12,13 +13,17 @@ repos = [
|
||||
"maidalun1020/bce-reranker-base_v1",
|
||||
]
|
||||
|
||||
|
||||
def download_model(repo_id):
|
||||
local_dir = os.path.join("huggingface.co", repo_id)
|
||||
local_dir = os.path.abspath(os.path.join("huggingface.co", repo_id))
|
||||
os.makedirs(local_dir, exist_ok=True)
|
||||
snapshot_download(repo_id=repo_id, local_dir=local_dir)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
local_dir = os.path.abspath('nltk_data')
|
||||
for data in ['wordnet', 'punkt', 'wordnet']:
|
||||
print(f"Downloading nltk {data}...")
|
||||
nltk.download(data, download_dir=local_dir)
|
||||
for repo_id in repos:
|
||||
print(f"Downloading huggingface repo {repo_id}...")
|
||||
download_model(repo_id)
|
||||
|
||||
Reference in New Issue
Block a user