Kinetica는 vector 유사도 검색을 통합 지원하는 데이터베이스입니다
지원 기능:
  • 정확한 최근접 이웃 검색 및 근사 최근접 이웃 검색
  • L2 distance, inner product, cosine distance
이 노트북은 Kinetica vector store(Kinetica)를 기반으로 한 retriever 사용 방법을 보여줍니다. 
# Please ensure that this connector is installed in your working environment.
pip install gpudb==7.2.0.9
OpenAIEmbeddings를 사용하려면 OpenAI API Key를 가져와야 합니다. 
import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

## Loading Environment Variables
from dotenv import load_dotenv

load_dotenv()

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import (
    Kinetica,
    KineticaSettings,
)
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

# Kinetica needs the connection to the database.
# This is how to set it up.
HOST = os.getenv("KINETICA_HOST", "http://127.0.0.1:9191")
USERNAME = os.getenv("KINETICA_USERNAME", "")
PASSWORD = os.getenv("KINETICA_PASSWORD", "")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "")


def create_config() -> KineticaSettings:
    return KineticaSettings(host=HOST, username=USERNAME, password=PASSWORD)

​
vector store에서 Retriever 생성하기

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# The Kinetica Module will try to create a table with the name of the collection.
# So, make sure that the collection name is unique and the user has the permission to create a table.

COLLECTION_NAME = "state_of_the_union_test"
connection = create_config()

db = Kinetica.from_documents(
    embedding=embeddings,
    documents=docs,
    collection_name=COLLECTION_NAME,
    config=connection,
)

# create retriever from the vector store
retriever = db.as_retriever(search_kwargs={"k": 2})

​
retriever로 검색하기

result = retriever.get_relevant_documents(
    "What did the president say about Ketanji Brown Jackson"
)
print(docs[0].page_content)
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I