Agent with Knowledge Base

Code

1"""Run `uv pip install sqlalchemy pgvector pypdf openai` to install dependencies."""
2import asyncio
3from kern.agent import Agent
4from kern.knowledge.embedder.azure_openai import AzureOpenAIEmbedder
5from kern.knowledge.knowledge import Knowledge
6from kern.models.azure import AzureAIFoundry
7from kern.vectordb.pgvector import PgVector
8
9db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
10
11knowledge = Knowledge(
12    vector_db=PgVector(
13        table_name="recipes",
14        db_url=db_url,
15        embedder=AzureOpenAIEmbedder(),
16    ),
17)
18# Add content to the knowledge
19asyncio.run(knowledge.ainsert(
20    url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
21))
22
23agent = Agent(
24    model=AzureAIFoundry(id="Cohere-command-r-08-2024"),
25    knowledge=knowledge,
26)
27agent.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_API_KEY=xxx
2export AZURE_ENDPOINT=xxx

Install dependencies

1uv pip install -U azure-ai-inference 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/ai_foundry/knowledge.py