Agent with Knowledge Base

Code

1import asyncio
2from kern.agent import Agent
3from kern.knowledge.embedder.azure_openai import AzureOpenAIEmbedder
4from kern.knowledge.knowledge import Knowledge
5from kern.models.azure import AzureOpenAI
6from kern.vectordb.pgvector import PgVector
7
8db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
9
10knowledge = Knowledge(
11    vector_db=PgVector(
12        table_name="recipes",
13        db_url=db_url,
14        embedder=AzureOpenAIEmbedder(),
15    ),
16)
17# Add content to the knowledge
18asyncio.run(knowledge.ainsert(
19    url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
20))
21
22agent = Agent(
23    model=AzureOpenAI(id="gpt-5-mini"),
24    knowledge=knowledge,
25)
26agent.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

Set your API key

1export AZURE_OPENAI_API_KEY=xxx
2export AZURE_OPENAI_ENDPOINT=xxx
3export AZURE_DEPLOYMENT=xxx

Install dependencies

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

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/azure/openai/knowledge.py