Skip to main content
The PgVector Agent uses PgVector as Knowledge Base and Storage for the Agent. 
from phi.agent import Agent
from phi.storage.agent.postgres import PgAgentStorage
from phi.knowledge.pdf import PDFUrlKnowledgeBase
from phi.vectordb.pgvector import PgVector

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

agent = Agent(
    storage=PgAgentStorage(table_name="recipe_agent", db_url=db_url),
    knowledge_base=PDFUrlKnowledgeBase(
        urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
        vector_db=PgVector(table_name="recipe_documents", db_url=db_url),
    ),
    # Show tool calls in the response
    show_tool_calls=True,
    # Enable the agent to search the knowledge base
    search_knowledge=True,
    # Enable the agent to read the chat history
    read_chat_history=True,
)
# Comment out after first run
agent.knowledge_base.load(recreate=False)  # type: ignore

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

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate
2

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 \
  phidata/pgvector:16
3

Install libraries

pip install -U pgvector pypdf "psycopg[binary]" sqlalchemy phidata
4

Run PgVector Agent

python cookbook/integrations/pgvector/agent.py

​
Information

⌘I