With Autonomous Agents, the LLM can run functions to:

  • Search the knowledge base
  • Search the chat history
  • Achieve other tasks

The LLM decides if it needs to search the knowledge base and what search parameters it needs to query the knowledge base.

from phi.agent import Agent
from phi.knowledge.pdf import PDFUrlKnowledgeBase
from phi.vectordb.pgvector import PgVector

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(
        table_name="recipes",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
)
# Comment out as the knowledge base is already loaded.
# knowledge_base.load(recreate=False)

agent = Agent(
    knowledge=knowledge_base,
    # 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,
)
agent.print_response("How do I make pad thai?", markdown=True)
agent.print_response("What was my last question?", markdown=True)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.

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 openai phidata
4

Run the agent

​
Information

Was this page helpful?

Agentic RAG with Hybrid SearchPDF Agent with Storage