ClickHouse

! docker run -d -p 8123:8123 -p 9000:9000 --name langchain-clickhouse-server --ulimit nofile=262144:262144 -e CLICKHOUSE_SKIP_USER_SETUP=1 clickhouse/clickhouse-server:25.7

pip install -qU langchain-community clickhouse-connect

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

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

from langchain_community.vectorstores import Clickhouse, ClickhouseSettings

settings = ClickhouseSettings(table="clickhouse_example")
vector_store = Clickhouse(embeddings, config=settings)

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))]

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

vector_store.delete(ids=uuids[-1])

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

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

meta = vector_store.metadata_column
results = vector_store.similarity_search_with_relevance_scores(
    "What did I eat for breakfast?",
    k=4,
    where_str=f"{meta}.source = 'tweet'",
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 1, "score_threshold": 0.5},
)
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})