​
Code

cookbook/models/azure/ai_foundry/knowledge.py
from agno.agent import Agent
from agno.embedder.azure_openai import AzureOpenAIEmbedder
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.models.azure import AzureAIFoundry
from agno.vectordb.pgvector import PgVector

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

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(
        table_name="recipes",
        db_url=db_url,
        embedder=AzureOpenAIEmbedder(id="text-embedding-3-small"),
    ),
)
knowledge_base.load(recreate=False)  # Comment out after first run

agent = Agent(
    model=AzureAIFoundry(id="Cohere-command-r-08-2024"),
    knowledge=knowledge_base,
    show_tool_calls=True,
    debug_mode=True,
)
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

Set your API key

export AZURE_API_KEY=xxx
export AZURE_ENDPOINT=xxx
3

Install libraries

pip install -U azure-ai-inference agno duckduckgo-search sqlalchemy pgvector pypdf
4

Run PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:16
5

Run Agent

python cookbook/models/azure/ai_foundry/knowledge.py
Basic StreamingAgent with Storage