mirror of
				https://github.com/infiniflow/ragflow.git
				synced 2025-11-03 19:29:43 +00:00 
			
		
		
		
	### What problem does this PR solve? Added tika jar into image to avoid downloading. Close #3017 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
		
			
				
	
	
		
			44 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			44 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
#!/usr/bin/env python3
 | 
						|
 | 
						|
from huggingface_hub import snapshot_download
 | 
						|
import nltk
 | 
						|
import os
 | 
						|
import urllib.request
 | 
						|
 | 
						|
urls = [
 | 
						|
    "http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb",
 | 
						|
    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar",
 | 
						|
    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar.md5",
 | 
						|
]
 | 
						|
 | 
						|
repos = [
 | 
						|
    "InfiniFlow/text_concat_xgb_v1.0",
 | 
						|
    "InfiniFlow/deepdoc",
 | 
						|
    "BAAI/bge-large-zh-v1.5",
 | 
						|
    "BAAI/bge-reranker-v2-m3",
 | 
						|
    "maidalun1020/bce-embedding-base_v1",
 | 
						|
    "maidalun1020/bce-reranker-base_v1",
 | 
						|
]
 | 
						|
 | 
						|
def download_model(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__":
 | 
						|
    for url in urls:
 | 
						|
        filename = url.split("/")[-1]
 | 
						|
        print(f"Downloading {url}...")
 | 
						|
        if not os.path.exists(filename):
 | 
						|
            urllib.request.urlretrieve(url, filename)
 | 
						|
 | 
						|
    local_dir = os.path.abspath('nltk_data')
 | 
						|
    for data in ['wordnet', 'punkt', 'punkt_tab']:
 | 
						|
        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)
 |