Skip to main content

​
Code

cookbook/knowledge/vector_db/clickhouse_db/async_clickhouse.py
import asyncio

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

agent = Agent(
    knowledge=Knowledge(
        vector_db=Clickhouse(
            table_name="recipe_documents",
            host="localhost",
            port=8123,
            username="ai",
            password="ai",
        ),
    ),
    search_knowledge=True,
    read_chat_history=True,
)

if __name__ == "__main__":
    asyncio.run(
        agent.knowledge.add_content_async(url="https://docs.agno.com/introduction/agents.md")
    )

    asyncio.run(
        agent.aprint_response("What is the purpose of an Agno Agent?", markdown=True)
    )

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Install libraries

pip install -U clickhouse-connect pypdf openai agno
3

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
4

Set environment variables

export CLICKHOUSE_HOST="localhost"
export CLICKHOUSE_PORT="8123"
export CLICKHOUSE_USER="ai"
export CLICKHOUSE_PASSWORD="ai"
export CLICKHOUSE_DB="ai"
export OPENAI_API_KEY=xxx
5

Run Agent

python cookbook/knowledge/vector_db/clickhouse_db/async_clickhouse.py