Async Knowledge

Query a PgVector knowledge base asynchronously with a Llama 4 Maverick agent.

This example’s install docstring lists unused ddgs and omits openai plus psycopg[binary], which its default embedder and PostgreSQL URL require. Use the generated installation step below.

async_knowledge.py

"""Run `uv pip install ddgs sqlalchemy pgvector pypdf llama-api-client` to install dependencies."""

import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.models.meta import Llama
from agno.vectordb.pgvector import PgVector

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

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=Llama(id="Llama-4-Maverick-17B-128E-Instruct-FP8"), knowledge=knowledge
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    # Create and use the agent
    asyncio.run(agent.aprint_response("How to make Thai curry?", markdown=True))

Run the Example

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. Install dependencies

   uv pip install -U agno "psycopg[binary]" beautifulsoup4 llama-api-client openai pgvector pypdf sqlalchemy
   
3. Export your API keys

   Mac/Linux

   export LLAMA_API_KEY="your_llama_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:LLAMA_API_KEY="your_llama_api_key_here"
   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

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

   python async_knowledge.py
   

Full source: cookbook/90_models/meta/llama/async_knowledge.py