Kinetica 向量存储集成

# Pip install necessary package
pip install -qU langchain-kinetica

import getpass
import os

from langchain_openai import OpenAIEmbeddings

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

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

# Kinetica needs the connection to the database.
# Set these environment variables:
from gpudb import GPUdb

from langchain_kinetica import KineticaSettings, KineticaVectorstore

kdbc = GPUdb.get_connection()
k_config = KineticaSettings(kdbc=kdbc)
k_config

2026-02-02 21:28:34.745 INFO     [GPUdb] Connected to Kinetica! (host=http://localhost:19191 api=7.2.3.3 server=7.2.3.5)

KineticaSettings(kdbc=<gpudb.gpudb.GPUdb object at 0x1170ae270>, database='langchain', table='langchain_kinetica_embeddings', metric='l2')

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))]
uuids

['ddad79f1-141d-44f6-8f50-72e5c0f1ee16',
    '10819fa9-794b-4fde-934a-aabd453781c8',
    '3ce641d5-8c6b-4dcb-90fe-a3c19b3132ff',
    '9db5c865-389f-481c-aea2-440b8437e22c',
    '74dd4d80-a371-4c41-8254-7981d375274d',
    '74d7571e-f8c5-4001-9979-e99996ec2ce5',
    '3a3eb718-f2b9-4186-8c2e-34a1e18ebb3b',
    '59a88b08-f8c6-4cf5-b485-9485a4a8ffd0',
    'd84ad1c8-ec01-4d13-b61a-ef4b08abb485',
    'c9ab8f4f-e566-465f-a85d-ee05780714ea']

COLLECTION_NAME = "langchain_example"

vectorstore = KineticaVectorstore(
    config=k_config,
    embedding_function=embeddings,
    collection_name=COLLECTION_NAME,
    pre_delete_collection=True,
)

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

print()
print("Similarity Search")
results = vectorstore.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 = vectorstore.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, emb_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=0.945353] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]

vectorstore = KineticaVectorstore(
    config=k_config,
    embedding_function=embeddings,
    collection_name=COLLECTION_NAME,
)

# We can add documents to the existing vectorstore.
vectorstore.add_documents([Document(page_content="foo")])

docs_with_score = vectorstore.similarity_search_with_score("foo")

print(f"First result: {docs_with_score[0]}")
print(f"Second result: {docs_with_score[1]}")

First result: (Document(metadata={}, page_content='foo'), 0.0014664357295259833)
Second result: (Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!'), 1.260981559753418)

vectorstore = KineticaVectorstore.from_documents(
    documents=documents,
    embedding=embeddings,
    collection_name=COLLECTION_NAME,
    config=k_config,
    pre_delete_collection=True,
)

docs_with_score = vectorstore.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!'),
    1.2609236240386963)

from langchain_core.vectorstores.base import VectorStoreRetriever

retriever: VectorStoreRetriever = vectorstore.as_retriever()
retriever

VectorStoreRetriever(tags=['KineticaVectorstore', 'OpenAIEmbeddings'], vectorstore=<langchain_kinetica.vectorstores.KineticaVectorstore object at 0x1139cfaa0>, search_kwargs={})