Code
cookbook/11_models/vllm/memory.py
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.vllm import VLLM
from agno.utils.pprint import pprint
# Change this if your Postgres container is running elsewhere
DB_URL = "postgresql+psycopg://ai:ai@localhost:5532/ai"
agent = Agent(
model=VLLM(id="microsoft/Phi-3-mini-128k-instruct"),
db=PostgresDb(db_url=DB_URL),
update_memory_on_run=True,
enable_session_summaries=True,
)
# -*- Share personal information
agent.print_response("My name is john billings", stream=True)
# -*- Print memories and summary
if agent.db:
pprint(agent.get_user_memories(user_id="test_user"))
pprint(
agent.get_session(session_id="test_session").summary # type: ignore
)
# -*- Share personal information
agent.print_response("I live in nyc", stream=True)
# -*- Print memories and summary
if agent.db:
pprint(agent.get_user_memories(user_id="test_user"))
pprint(
agent.get_session(session_id="test_session").summary # type: ignore
)
# -*- Share personal information
agent.print_response("I'm going to a concert tomorrow", stream=True)
# -*- Print memories and summary
if agent.db:
pprint(agent.get_user_memories(user_id="test_user"))
pprint(
agent.get_session(session_id="test_session").summary # type: ignore
)
# Ask about the conversation
agent.print_response(
"What have we been talking about, do you know my name?", stream=True
)
Ensure Postgres database is running.
Usage
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Start Postgres database
./cookbook/scripts/run_pgvector.sh
3
Install Libraries
uv pip install -U agno openai vllm sqlalchemy psycopg pgvector
4
Start vLLM server
vllm serve microsoft/Phi-3-mini-128k-instruct \
--dtype float32 \
--enable-auto-tool-choice \
--tool-call-parser pythonic
5
Run Agent
python cookbook/11_models/vllm/memory.py