PgVector

Code

cookbook/08_knowledge/vector_db/pgvector/pgvector_db.py

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

vector_db = PgVector(table_name="vectors", db_url=db_url)

knowledge = Knowledge(
    name="My PG Vector Knowledge Base",
    description="This is a knowledge base that uses a PG Vector DB",
    vector_db=vector_db,
)
knowledge.insert(
    name="Recipes",
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
    metadata={"doc_type": "recipe_book"},
)

agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
    read_chat_history=True,
)

agent.print_response("How do I make pad thai?", markdown=True)

vector_db.delete_by_name("Recipes")

vector_db.delete_by_metadata({"doc_type": "recipe_book"})

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

   uv pip install -U psycopg2-binary pgvector pypdf openai agno
   
3. Run PgVector on Docker
4. Create a file resources.py with the following contents:
5. from agno.docker.app.postgres import PgVectorDb
   from agno.docker.resources import DockerResources
   
   # -*- PgVector running on port 5432:5432
   vector_db = PgVectorDb(
       pg_user="ai",
       pg_password="ai",
       pg_database="ai",
       debug_mode=True,
   )
   
   # -*- DockerResources
   dev_docker_resources = DockerResources(apps=[vector_db])
   

6. Start resources using:
7. Mac

   ag start resources.py
   

   Windows

   ag start resources.py
   
8. Press Enter to confirm and verify container status on the docker dashboard.
9. Set environment variables

   export OPENAI_API_KEY=xxx
   
10. Run Agent

    python cookbook/08_knowledge/vector_db/pgvector/pgvector_db.py