Agent with Knowledge Base

Code

cookbook/models/cerebras/basic_knowledge.py

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.models.cerebras import Cerebras
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),
)
knowledge_base.load(recreate=True)  # Comment out after first run

agent = Agent(
    model=Cerebras(id="llama-4-scout-17b-16e-instruct"),
    knowledge=knowledge_base,
)
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.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API key

   export CEREBRAS_API_KEY=xxx
   
3. Install libraries

   pip install -U agno cerebras-cloud-sdk
   
4. Start your Postgres server

   Ensure your Postgres server is running and accessible at the connection string used in db_url.

5. Run Agent (first time)

   The first run will load and index the PDF. This may take a while.

   Mac

   python cookbook/models/cerebras/basic_knowledge.py
   
6. Subsequent Runs

   After the first run, comment out or remove knowledge_base.load(recreate=True) to avoid reloading the PDF each time.