Generative AI
Implementation of Coding to Build an In-Memory Agent Infrastructure for Continuous Multi-User and Multi-session Applications LLM
banner("Part 5 — Streaming")
mem.attribution(entity_id="[email protected]", process_id="personal-assistant")
stream = client.chat.completions.create(
model=MODEL,
messages=[{"role": "user",
"content": "In two sentences, what do you remember about me?"}],
stream=True,
)
print("[stream] ", end="")
for chunk in stream:
d = chunk.choices[0].delta.content
if d: print(d, end="", flush=True)
print(); time.sleep(WRITE_DELAY)
banner("Part 6 — Async LLM calls")
async def async_demo():
r = await async_client.chat.completions.create(
model=MODEL,
messages=[{"role": "user",
"content": "What dietary restriction do I have? (asked async)"}],
)
return r.choices[0].message.content
print("[async]", asyncio.run(async_demo()))
banner("Part 7 — Mini support agent across multiple sessions")
def support(user_id, prompt):
mem.attribution(entity_id=user_id, process_id="support-bot")
return ask(prompt, system=(
"You are a calm, helpful customer support agent. "
"Use what you remember about the user. If you don't know, say so."
))
USER = "[email protected]"
mem.attribution(entity_id=USER, process_id="support-bot")
mem.new_session()
print("[support T1]", support(USER,
"Hi! I'm Charlie, on the Pro plan. Email: [email protected]. "
"Billing question for next month."))
time.sleep(WRITE_DELAY)
mem.new_session()
print("[support T2]", support(USER,
"Hey, me again. What plan am I on and what's my email of record?"))
banner("Done. Open to inspect memories, "
"or use Memori BYODB to point at your own Postgres.")
