Spaces:
Sleeping
Sleeping
File size: 7,543 Bytes
922d194 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
"""
Script to store FAISS and pickle files in Azure Cosmos DB MongoDB API
This script should be run only once to upload the vector database files.
run this at root of the project:
python -m app.services.chatbot.vectorDB_upload_script
"""
import os
import asyncio
from motor.motor_asyncio import AsyncIOMotorClient, AsyncIOMotorGridFSBucket
from datetime import datetime
import logging
from dotenv import load_dotenv
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Load environment variables from .env
load_dotenv()
# Database configuration
MONGO_URI = os.getenv("MONGODB_KEY")
DB_NAME = "SysmodelerDB"
BUCKET_NAME = "vector_db"
# File paths
FAISS_PATH = r"c:\Users\User\Downloads\faiss_index_sysml\index.faiss"
PICKLE_PATH = r"c:\Users\User\Downloads\faiss_index_sysml\index.pkl"
class VectorDBUploader:
def __init__(self):
self.client = None
self.db = None
self.fs = None
async def connect(self):
"""Connect to MongoDB"""
try:
self.client = AsyncIOMotorClient(MONGO_URI)
self.db = self.client[DB_NAME]
self.fs = AsyncIOMotorGridFSBucket(self.db, bucket_name=BUCKET_NAME)
# Test connection
await self.client.admin.command('ping')
logger.info("Successfully connected to MongoDB")
return True
except Exception as e:
logger.error(f"Failed to connect to MongoDB: {e}")
return False
async def file_exists(self, filename: str) -> bool:
"""Check if file already exists in GridFS"""
try:
async for file_doc in self.fs.find({"filename": filename}):
return True
return False
except Exception as e:
logger.error(f"Error checking file existence: {e}")
return False
# async def upload_file(self, file_path: str, filename: str) -> bool:
# """Upload a file to GridFS"""
# try:
# # Check if file exists locally
# if not os.path.exists(file_path):
# logger.error(f"Local file not found: {file_path}")
# return False
# # Check if file already exists in database
# if await self.file_exists(filename):
# logger.warning(f"File {filename} already exists in database. Skipping...")
# return True
# # Get file size for logging
# file_size = os.path.getsize(file_path)
# logger.info(f"Uploading {filename} ({file_size} bytes)...")
# # Upload file
# with open(file_path, 'rb') as f:
# file_id = await self.fs.upload_from_stream(
# filename,
# f,
# metadata={
# "uploaded_at": datetime.utcnow(),
# "original_path": file_path,
# "file_size": file_size,
# "description": f"Vector database file: {filename}"
# }
# )
# logger.info(f"Successfully uploaded {filename} with ID: {file_id}")
# return True
# except Exception as e:
# logger.error(f"Failed to upload {filename}: {e}")
# return False
async def upload_file(self, file_path: str, filename: str) -> bool:
"""Upload a file to GridFS, overwriting any existing files with the same name"""
try:
# Check if file exists locally
if not os.path.exists(file_path):
logger.error(f"Local file not found: {file_path}")
return False
# Remove any existing file with the same name
async for file_doc in self.fs.find({"filename": filename}):
await self.fs.delete(file_doc._id)
logger.info(f"Deleted existing file: {filename} (ID: {file_doc._id})")
# Get file size for logging
file_size = os.path.getsize(file_path)
logger.info(f"Uploading {filename} ({file_size} bytes)...")
# Upload file
with open(file_path, 'rb') as f:
file_id = await self.fs.upload_from_stream(
filename,
f,
metadata={
"uploaded_at": datetime.utcnow(),
"original_path": file_path,
"file_size": file_size,
"description": f"Vector database file: {filename}"
}
)
logger.info(f"Successfully uploaded {filename} with ID: {file_id}")
return True
except Exception as e:
logger.error(f"Failed to upload {filename}: {e}")
return False
async def list_files(self):
"""List all files in the GridFS bucket"""
try:
logger.info(f"Files in {BUCKET_NAME} bucket:")
async for file_doc in self.fs.find():
logger.info(f"- {file_doc.filename} (ID: {file_doc._id}, Size: {file_doc.length} bytes)")
except Exception as e:
logger.error(f"Failed to list files: {e}")
async def upload_vector_files(self):
"""Upload both FAISS and pickle files"""
files_to_upload = [
(FAISS_PATH, "index.faiss"),
(PICKLE_PATH, "index.pkl")
]
success_count = 0
for file_path, filename in files_to_upload:
if await self.upload_file(file_path, filename):
success_count += 1
else:
logger.error(f"Failed to upload {filename}")
logger.info(f"Upload completed: {success_count}/{len(files_to_upload)} files uploaded successfully")
return success_count == len(files_to_upload)
async def close(self):
"""Close database connection"""
if self.client:
self.client.close()
logger.info("Database connection closed")
async def main():
"""Main function to upload vector database files"""
uploader = VectorDBUploader()
try:
# Connect to database
if not await uploader.connect():
logger.error("Failed to connect to database. Exiting...")
return
# Upload files
logger.info("Starting vector database files upload...")
success = await uploader.upload_vector_files()
if success:
logger.info("All files uploaded successfully!")
else:
logger.error("Some files failed to upload")
# List all files in the bucket
await uploader.list_files()
except Exception as e:
logger.error(f"Unexpected error: {e}")
finally:
await uploader.close()
if __name__ == "__main__":
print("Vector Database File Uploader")
print("=" * 50)
print(f"Database: {DB_NAME}")
print(f"Bucket: {BUCKET_NAME}")
print(f"FAISS file: {FAISS_PATH}")
print(f"Pickle file: {PICKLE_PATH}")
print("=" * 50)
# Run the upload process
asyncio.run(main())
|