​
Code

cookbook/models/ollama/knowledge.py
from agno.agent import Agent
from agno.knowledge.embedder.ollama import OllamaEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.ollama import Ollama
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="recipes",
        db_url=db_url,
        embedder=OllamaEmbedder(id="llama3.2", dimensions=3072),
    ),
)
# Add content to the knowledge
knowledge.add_content(
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
)

agent = Agent(model=Ollama(id="llama3.2"), knowledge=knowledge)
agent.print_response("How to make Thai curry?", 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 Ollama

Follow the Ollama installation guide and run:
ollama pull llama3.2
3

Install libraries

pip install -U agno ddgs sqlalchemy pgvector pypdf openai ollama
4

Run Agent

python cookbook/models/ollama/knowledge.py