Kinetica Vectorstore API

# Pip install necessary package
pip install -qU  langchain-openai langchain-community
pip install "gpudb>=7.2.2.0"
pip install -qU  tiktoken

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()

False

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import (
    Kinetica,
    KineticaSettings,
)
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

# 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)

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

# 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 = "langchain_example"
connection = create_config()

db = Kinetica(
    connection,
    embeddings,
    collection_name=COLLECTION_NAME,
)

db.add_documents(documents=documents, ids=uuids)

['05e5a484-0273-49d1-90eb-1276baca31de',
 'd98b808f-dc0b-4328-bdbf-88f6b2ab6040',
 'ba0968d4-e344-4285-ae0f-f5199b56f9d6',
 'a25393b8-6539-45b5-993e-ea16d01941ec',
 '804a37e3-1278-4b60-8b02-36b159ee8c1a',
 '9688b594-3dc6-41d2-a937-babf8ff24c2f',
 '40f7b8fe-67c7-489a-a5a5-7d3965e33bba',
 'b4fc1376-c113-41e9-8f16-f9320517bedd',
 '4d94d089-fdde-442b-84ab-36d9fe0670c8',
 '66fdb79d-49ce-4b06-901a-fda6271baf2a']

# query = "What did the president say about Ketanji Brown Jackson"
# docs_with_score = db.similarity_search_with_score(query)

print()
print("Similarity Search")
results = db.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    filter={"source": "tweet"},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

print()
print("Similarity search with score")
results = db.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, filter={"source": "news"}
)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

Similarity Search
* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

Similarity search with score
* [SIM=0.945397] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]

store = Kinetica(
    collection_name=COLLECTION_NAME,
    config=connection,
    embedding_function=embeddings,
)

store.add_documents([Document(page_content="foo")])

['68c4c679-c4d9-4f2d-bf01-f6c4f2181503']

docs_with_score = db.similarity_search_with_score("foo")

docs_with_score[0]

(Document(metadata={}, page_content='foo'), 0.0015394920483231544)

docs_with_score[1]

(Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!'),
 1.2609431743621826)

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

docs_with_score = db.similarity_search_with_score("foo")

docs_with_score[0]

(Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!'),
 1.260920763015747)

retriever = store.as_retriever()

print(retriever)

tags=['Kinetica', 'OpenAIEmbeddings'] vectorstore=<langchain_community.vectorstores.kinetica.Kinetica object at 0x7a48142b2230> search_kwargs={}