Agent with Knowledge

Answer questions from a PDF using a Nebius agent and PgVector.

Code

knowledge.py

import os

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

agent = Agent(model=Nebius(id=os.environ["NEBIUS_MODEL_ID"]), knowledge=knowledge)
agent.print_response("How to make Thai curry?", markdown=True)

Select a text-generation model with function-calling support for this example.

Usage

1. Set up your virtual environment

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Export environment variables

   Select an available text-generation model ID from the Nebius model-list API. PgVector uses OpenAIEmbedder by default, so this example also requires an OpenAI API key.

   macOS / Linux

   export NEBIUS_API_KEY="your_nebius_api_key"
   export NEBIUS_MODEL_ID="your_current_text_model_id"
   export OPENAI_API_KEY="your_openai_api_key"
   

   $Env:NEBIUS_API_KEY="your_nebius_api_key"
   $Env:NEBIUS_MODEL_ID="your_current_text_model_id"
   $Env:OPENAI_API_KEY="your_openai_api_key"
   
3. Install dependencies

   uv pip install -U openai agno sqlalchemy psycopg 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:18
   
5. Run Agent

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

   python knowledge.py