Storage and Memory

Combine PgVector knowledge, Postgres memory, session summaries, and web search on Gemini.

storage_and_memory.py

"""Run `pip install ddgs pgvector google.genai` to install dependencies."""

from agno.agent import Agent
from agno.db.postgres.postgres import PostgresDb
from agno.knowledge import PDFUrlKnowledgeBase
from agno.models.google import Gemini
from agno.tools.websearch import WebSearchTools
from agno.vectordb.pgvector import PgVector

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

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=Gemini(id="gemini-2.0-flash-001"),
    tools=[WebSearchTools()],
    knowledge=knowledge_base,
    # Store the memories and summary in a database
    db=PostgresDb(db_url=db_url, memory_table="agent_memory"),
    update_memory_on_run=True,
    enable_session_summaries=True,
    # This setting adds a tool to search the knowledge base for information
    search_knowledge=True,
    # This setting adds a tool to get chat history
    read_chat_history=True,
    # Add the previous chat history to the messages sent to the Model.
    add_history_to_context=True,
    # This setting adds 6 previous messages from chat history to the messages sent to the LLM
    num_history_runs=6,
    markdown=True,
)
agent.print_response("Whats is the latest AI news?")

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

if __name__ == "__main__":
    pass

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]" ddgs google-genai openai pgvector pypdf sqlalchemy
   
3. Export your API keys

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:GOOGLE_API_KEY="your_google_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 storage_and_memory.py, then run:

   python storage_and_memory.py
   

Full source: cookbook/90_models/google/gemini/storage_and_memory.py