File size: 1,949 Bytes
6ba8078 |
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 |
from dotenv import load_dotenv
import pandas as pd
import os
import pymongo
from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch
from langchain_huggingface import HuggingFaceEmbeddings
__author__ = "Chirag Kamble"
class DBConnect:
"""
Class to connect to the database
"""
@staticmethod
def connect_db():
"""
Static method to connect to the database and create a vector store
:return: mongodb_vector_store: MongoDB Atlas Vector Store instance connected to the required mongodb collection
:return: movies: dataframe containing all movies in the database
"""
load_dotenv()
mongodb_connection_url = os.getenv("MONGODB_CONNECTION_URL")
mongodb_db_name: str = os.getenv("MONGODB_DB_NAME")
mongodb_collection_name: str = os.getenv("MONGODB_COLLECTION_NAME")
mongodb_vector_index: str = os.getenv("MONGODB_VECTOR_INDEX_NAME")
text_key: str = os.getenv("TEXT_KEY")
embedding_key: str = os.getenv("EMBEDDING_KEY")
relevance_score_fn = os.getenv("RELEVANCE_SCORE_FN")
client = pymongo.MongoClient(mongodb_connection_url)
db = client[mongodb_db_name]
collection = db[mongodb_collection_name]
mongodb_vector_store = MongoDBAtlasVectorSearch(collection=collection,
embedding=HuggingFaceEmbeddings(),
index_name=mongodb_vector_index,
relevance_score_fn=relevance_score_fn,
text_key=text_key,
embedding_key=embedding_key,
)
movies_docs = collection.find()
movies = pd.DataFrame(movies_docs)
return mongodb_vector_store, movies
|