Agent with Knowledge Base

Search a PgVector knowledge base from an Azure AI Foundry agent.

Classic adapter: its SDK is retired. See the migration example.

Code

For an existing classic endpoint, use an available Command A deployment named Cohere-command-a, or set id to your actual compatible deployment name. The older Command R August 2024 model retired on May 12, 2026; see the model schedule.

from agno.agent import Agent
from agno.knowledge.embedder.azure_openai import AzureOpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.azure import AzureAIFoundry
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=AzureOpenAIEmbedder(),
    ),
)
# Add content to the knowledge
knowledge.insert(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf")

agent = Agent(
    model=AzureAIFoundry(id="Cohere-command-a"),
    knowledge=knowledge,
)
agent.print_response("How to make Thai curry?", markdown=True)

Usage

The AzureOpenAIEmbedder() example also needs a separate text-embedding-3-small deployment (1536 dimensions). Set AZURE_EMBEDDER_DEPLOYMENT to that deployment name, with its own resource endpoint and key in the AZURE_EMBEDDER_OPENAI_* variables, before starting Python. These settings are independent of the chat deployment.

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API keys

export AZURE_API_KEY=xxx
export AZURE_ENDPOINT=xxx
# For the AzureOpenAIEmbedder
export AZURE_EMBEDDER_OPENAI_API_KEY=xxx
export AZURE_EMBEDDER_OPENAI_ENDPOINT=xxx
export AZURE_EMBEDDER_DEPLOYMENT="your_embedding_deployment"

Install dependencies

uv pip install -U azure-ai-inference aiohttp openai sqlalchemy pgvector pypdf "psycopg[binary]" agno

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:18

Run Agent

Save the code above as knowledge.py, then run:

python knowledge.py