Hackathons/Hoya26
1
0
Fork 0
mirror of https://github.com/SirBlobby/Hoya26.git synced 2026-02-04 03:34:34 -05:00
Code Issues Packages Projects Releases Wiki Activity

Populate DB Chromadb

Browse Source
This commit is contained in:
default
2026-01-24 07:52:48 +00:00
parent d145f7e94c
commit 4298368b63
10 changed files with 279 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
backend/scripts/populate_db.py
View File

@@ -1,8 +1,8 @@
import os
import sys
import argparse
from pathlib import Path
# Add backend directory to path so we can import src
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
from dotenv import load_dotenv
@@ -10,21 +10,23 @@ load_dotenv()
from src.rag.ingest import process_file
from src.rag.store import ingest_documents
from src.mongo.vector_store import is_file_processed, log_processed_file
from src.mongo.metadata import is_file_processed, log_processed_file
def populate_from_dataset(dataset_dir):
def populate_from_dataset(dataset_dir, category=None):
dataset_path = Path(dataset_dir)
if not dataset_path.exists():
print(f"Dataset directory not found: {dataset_dir}")
return
print(f"Scanning {dataset_dir}...")
if category:
print(f"Category: {category}")
total_chunks = 0
files_processed = 0
for file_path in dataset_path.glob('*'):
if file_path.is_file() and file_path.suffix.lower() in ['.csv', '.pdf']:
if file_path.is_file() and file_path.suffix.lower() in ['.csv', '.pdf', '.txt', '.xlsx']:
if is_file_processed(file_path.name):
print(f"Skipping {file_path.name} (already processed)")
continue
@@ -33,10 +35,10 @@ def populate_from_dataset(dataset_dir):
try:
chunks = process_file(str(file_path))
if chunks:
count = ingest_documents(chunks)
count = ingest_documents(chunks, source_file=file_path.name, category=category)
print(f" Ingested {count} chunks.")
if count > 0:
log_processed_file(file_path.name)
log_processed_file(file_path.name, category=category, chunk_count=count)
total_chunks += count
files_processed += 1
else:
@@ -47,6 +49,14 @@ def populate_from_dataset(dataset_dir):
print(f"\nFinished! Processed {files_processed} files. Total chunks ingested: {total_chunks}")
if __name__ == "__main__":
# Assuming run from backend/
dataset_dir = os.path.join(os.path.dirname(__file__), '../dataset')
populate_from_dataset(dataset_dir)
parser = argparse.ArgumentParser(description="Populate vector database from dataset files")
parser.add_argument("--category", "-c", type=str, help="Category to assign to ingested documents")
parser.add_argument("--dir", "-d", type=str, default=None, help="Dataset directory path")
args = parser.parse_args()
if args.dir:
dataset_dir = args.dir
else:
dataset_dir = os.path.join(os.path.dirname(__file__), '../dataset')
populate_from_dataset(dataset_dir, category=args.category)