insert_data.py

from config import COLLECTION_NAME
import os
import csv
from qdrant_client.http.models import VectorParams, PointStruct
from dotenv import load_dotenv
from generate_embedding import get_book_vector
from connect_qdrant import get_qdrant_client

load_dotenv()
qdrant_client = get_qdrant_client()

# Read and insert documents from CSV
csv_file_path = "/mnt/c/Users/SUPERADMIN/book-hunt-engine/data/books.csv"
with open(csv_file_path, newline='', encoding='utf-8') as csvfile:
    reader = csv.DictReader(csvfile)
    for row in reader:
        doc_id = int(row["isbn13"])
        vector = get_book_vector(row)
        payload = {
            "title": row["title"],
            "isbn10": row["isbn10"],
            "isbn13": row["isbn13"],
            "categories": row["categories"],
            "thumbnail": row["thumbnail"],
            "description": row["description"],
            "num_pages": int(row["num_pages"]),
            "average_rating": float(row["average_rating"]),
            "published_year": int(row["published_year"]),
            "authors": row["authors"].split(", ")
        }
        qdrant_client.upsert(
            collection_name=COLLECTION_NAME,
            points=[
                PointStruct(
                    id=doc_id,
                    vector=vector,
                    payload=payload
                )
            ]
        )
print("Documents added successfully.")