ClickHouse

Insert a PDF into a ClickHouse knowledge base, query it with an agent, and delete content by name or metadata.

Code

clickhouse_db.py
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.clickhouse import Clickhouse

vector_db = Clickhouse(
    table_name="recipe_documents",
    host="localhost",
    port=8123,
    username="ai",
    password="ai",
)

knowledge = Knowledge(
    name="My Clickhouse Knowledge Base",
    description="This is a knowledge base that uses a Clickhouse DB",
    vector_db=vector_db,
)

knowledge.insert(
    name="Recipes",
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
    metadata={"doc_type": "recipe_book"},
)

agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
    read_chat_history=True,
)

agent.print_response("How do I make pad thai?", markdown=True)

vector_db.delete_by_name("Recipes")
# or
vector_db.delete_by_metadata({"doc_type": "recipe_book"})

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U "clickhouse-connect[async]" pypdf openai agno

Run ClickHouse

docker run -d \
-e CLICKHOUSE_DB=ai \
-e CLICKHOUSE_USER=ai \
-e CLICKHOUSE_PASSWORD=ai \
-e CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1 \
-v clickhouse_data:/var/lib/clickhouse/ \
-v clickhouse_log:/var/log/clickhouse-server/ \
-p 8123:8123 \
-p 9000:9000 \
--ulimit nofile=262144:262144 \
--name clickhouse-server \
clickhouse/clickhouse-server

Set environment variables

export OPENAI_API_KEY=xxx

Run Agent

python clickhouse_db.py