Agent with Knowledge

Code

1from kern.agent import Agent
2from kern.knowledge.embedder.ollama import OllamaEmbedder
3from kern.knowledge.knowledge import Knowledge
4from kern.models.lmstudio import LMStudio
5from kern.vectordb.pgvector import PgVector
6
7db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
8
9knowledge_base = Knowledge(
10    vector_db=PgVector(
11        table_name="recipes",
12        db_url=db_url,
13        embedder=OllamaEmbedder(id="llama3.2", dimensions=3072),
14    ),
15)
16knowledge_base.insert(
17  url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
18)
19
20agent = Agent(
21    model=LMStudio(id="qwen2.5-7b-instruct-1m"),
22    knowledge=knowledge_base,
23    )
24agent.print_response("How to make Thai curry?", markdown=True)

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 LM Studio

Install LM Studio from here and download the model you want to use.

Install dependencies

1uv pip install -U sqlalchemy pgvector pypdf kern-ai

Run PgVector

1docker run -d \
2  -e POSTGRES_DB=ai \
3  -e POSTGRES_USER=ai \
4  -e POSTGRES_PASSWORD=ai \
5  -e PGDATA=/var/lib/postgresql/data/pgdata \
6  -v pgvolume:/var/lib/postgresql/data \
7  -p 5532:5432 \
8  --name pgvector \
9  agnohq/pgvector:16

Run Agent

1python cookbook/11_models/lmstudio/knowledge.py