Agent with Knowledge

Code

cookbook/models/litellm/knowledge.py

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.models.litellm import LiteLLM
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=LiteLLM(id="gpt-4o"),
    knowledge=knowledge_base,
    show_tool_calls=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.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   

2. Set your API key

   export LITELLM_API_KEY=xxx
   

3. Install libraries

   pip install -U litellm openai agno
   

4. Run Agent

   Mac

   python cookbook/models/litellm/knowledge.py
   

Assistant

Responses are generated using AI and may contain mistakes.