memobase 0.0.1

Client library of MemoBase: manage user memory for your LLM applications

Manage user profile/memory for your LLM applications

🌬️ Does your AI forget your users?

MemoBase maintains long-term memory of your users, for your product.

🖼️ Do you understand the customers that using your AI?

MemoBase offers accurate user profile, involving many aspects of your users: Age, Education, Interests, Opinions...

Customize the aspects you want MemoBase to collect.

⌛️ Do you want users spend more time on your Apps?

MemoBase is working with some AI companion startups. They have observated increased chatting turns after adopting MemoBase, leading to higher user retention and subscription rate.

Get Started

1. Start your MemoBase Backend, you should have the below two things to continue:

   1. A project url. default to http://localhost:8019

   2. A project token. default to secret

2. Install the Python SDK: pip install memobase

3. Get ready to remember your customers now:

Make sure you're connected

from memobase import MemoBaseClient, ChatBlob

mb = MemoBaseClient("http://localhost:8019", "secret")
assert mb.ping()

User CURD

uid = mb.add_user({"any_key": "any_value"})
mb.update_user({"any_key": "any_value2"})
u = mb.get_user(uid)

print(u)

Delete: mb.delete(uid)

Single User Data

In MemoBase, all types of data are blobs to a user that can insert, get and delete:

messages = [
  {
      "role": "user",
      "content": "Hello, I'm Gus",
  },
  {
      "role": "assistant",
      "content": "Hi, nice to meet you, Gus!",
  }
]
bid = u.insert(ChatBlob(messages=messages))
print(u.get(bid))

Delete: u.delete(bid). Delete a blob will cause forgetting memories that only related to this blob.

"Flush it moment"

u.flush()

And what will you get?

print(u.profile())
# [UserProfile(topic="basic_info", sub_topic="name", content="Gus"),...]

u.profile() will return a list of profiles that are learned from this user, including topic, sub_topic and content. As you insert more blobs, the profiles will become better.

Why need a flush?

In MemoBase, we don't memoize users in hot path. We use buffer zones for the recent inserted blobs.

When the buffer zone is too large (e.g. 1024 tokens) or idle for a long time (e.g. 1 hour), MemoBase will flush the whole buffer into the memory. Or you can just manually decide when to flush (e.g. A chat session is closed in your App)

Why/Where should I use MemoBase?

Remember the users

By placing profiles into your AI (e.g. system prompt).

Demo

PROFILES = "\n".join([p.describe for p in u.profile()])

print(PROFILES)
# basic_info: name - Gus
# basic_info: age - 25
# ...
# interest: foods - Mexican cuisine
# psychological: goals - Build something that maybe useful
# ...

User analysis and tracking

Too much information is hidden in the conversations between users and AI, that's why you need a new data tracking method to record user preference and behavior.

Demo

PROFILES = u.profile()

def under_age_30(p):
  return p.sub_topic == "age" and int(p.content) < 30

def love_cat(p):
  return p.topic == "interest" and p.sub_topic == "pets" and "cat" in p.content

is_user_under_30 = (
    len([p for p in profiles if under_age_30(p)]) > 0
)
is_user_love_cat = (
  len([p for p in profiles if love_cat(p)]) > 0
)                       
...

Sell something to your customers.

Not everyone is looking for Grammarly, it's always nice to sell something your users might want.

Demo

def pick_an_ad(profiles):
  work_titles = [p for p in profiles if p.topic=="work" and p.sub_topic=="title"]
  if not len(work_titles):
    return None
  wt = work_titles[0].content
  if wt == "Software Engineer":
    return "Deep Learning Stuff"
  elif wt == "some job":
    return "some ads"
  ...