ClickHouse

Code

1from kern.agent import Agent
2from kern.knowledge.knowledge import Knowledge
3from kern.vectordb.clickhouse import Clickhouse
4
5vector_db = Clickhouse(
6    table_name="recipe_documents",
7    host="localhost",
8    port=8123,
9    username="ai",
10    password="ai",
11)
12
13knowledge = Knowledge(
14    name="My Clickhouse Knowledge Base",
15    description="This is a knowledge base that uses a Clickhouse DB",
16    vector_db=vector_db,
17)
18
19knowledge.insert(
20    name="Recipes",
21    url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
22    metadata={"doc_type": "recipe_book"},
23)
24
25agent = Agent(
26    knowledge=knowledge,
27    search_knowledge=True,
28    read_chat_history=True,
29)
30
31agent.print_response("How do I make pad thai?", markdown=True)
32
33vector_db.delete_by_name("Recipes")
34# or
35vector_db.delete_by_metadata({"doc_type": "recipe_book"})

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Install dependencies

1uv pip install -U clickhouse-connect pypdf openai kern-ai

Run ClickHouse

1docker run -d \
2-e CLICKHOUSE_DB=ai \
3-e CLICKHOUSE_USER=ai \
4-e CLICKHOUSE_PASSWORD=ai \
5-e CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1 \
6-v clickhouse_data:/var/lib/clickhouse/ \
7-v clickhouse_log:/var/log/clickhouse-server/ \
8-p 8123:8123 \
9-p 9000:9000 \
10--ulimit nofile=262144:262144 \
11--name clickhouse-server \
12clickhouse/clickhouse-server

Set environment variables

1export CLICKHOUSE_HOST="localhost"
2export CLICKHOUSE_PORT="8123"
3export CLICKHOUSE_USER="ai"
4export CLICKHOUSE_PASSWORD="ai"
5export CLICKHOUSE_DB="ai"
6export OPENAI_API_KEY=xxx

Run Agent

1python cookbook/08_knowledge/vector_db/clickhouse_db/clickhouse.py