Build a MemGPT Discord Agent in LangGraph Cloud

Поделиться
HTML-код
  • Опубликовано: 30 июл 2024
  • In this tutorial, we create a MemGPT-inspired Discord agent using LangGraph Cloud, enabling chatbots to remember user interactions across conversations for a more personalized experience.
    Key components of the MemGPT agent:
    1. Core memories: Persistent user information
    2. Recall (semantic memories): Context-based retrieval
    3. Management via tool use
    We'll cover:
    - Implementing the agent graph
    - Deploying the agent on LangGraph Cloud
    - Creating the Discord bot
    - Writing tests and evaluations for the agent
    By the end of this tutorial, you'll understand how to build, deploy, and evaluate a Discord bot with long-term memory capabilities.
    Chapters:
    00:00 MemGPT & LangGraph Cloud
    00:36 Agent Overview
    01:19 Part 1: Designing the agent
    02:05 Forking and Cloning the Repository
    02:17 Understanding the Repo Structure
    03:05 Code Review: Defining Memory Management Tools
    07:15 Part 1b: Deploying on LangGraph Cloud
    08:59 Interacting with the Agent in LangGraph Cloud Studio
    09:47 Part 2: Deploying a Discord Server
    10:31 Setting Up a Discord Bot
    12:19 Testing the Discord Bot
    14:14 Setting Up Google Cloud Run
    15:12 Part 3: Evaluating and Testing the Agent
    17:14 Conclusion and Next Steps
    Additional Resources:
    - GitHub Repository: github.com/langchain-ai/lang-...
    - LangGraph Cloud Documentation: langchain-ai.github.io/langgr...
    - MemGPT Paper: arxiv.org/abs/2310.08560
    Presenter: Will Hinthorn ( / whinthorn )
  • НаукаНаука

Комментарии • 15

  • @andydataguy
    @andydataguy 27 дней назад +3

    This is epic! Glad to see you put memgpt together. Fingers crossed to get access to langgraph cloud soon 💜

  • @arush7169
    @arush7169 24 дня назад +2

    Awesome walkthrough! It\'d be fantastic to see some advanced TypeScript examples. I\'m interested in creating a robust help desk solution.

  • @Ankitamahato-ze5ix
    @Ankitamahato-ze5ix 24 дня назад +2

    Great video! I\'d love to see more TypeScript content. Could you do an advanced tutorial on integrating LangChain into a support ticketing system?

  • @IdPreferNot1
    @IdPreferNot1 26 дней назад +2

    Want to commit to LangGraph for agents but no LangGraph Cloud access :(

  • @kapilsonawane2208
    @kapilsonawane2208 24 дня назад +1

    Thanks for the great content! More TypeScript tutorials would be super useful, especially if you cover complex applications like support ticket management systems.

  • @Vimlesh-qf8fw
    @Vimlesh-qf8fw 24 дня назад +1

    Loving these LangChain videos! Can you include some advanced TypeScript tutorials? Specifically, something on developing a custom support platform would be great.

  • @lala-kq5ho
    @lala-kq5ho 27 дней назад +1

    MemGPT is amazing

  • @AdityaKumar-zt4rz
    @AdityaKumar-zt4rz 24 дня назад +1

    This was really helpful, thanks! Any chance you could cover more TypeScript, especially how to build a sophisticated customer service system?

  • @robboerman9378
    @robboerman9378 21 день назад

    Oof, this is so cool. So many ideas triggered ❤ if only I could use LanGraph Cloud 😢

  • @ikurious
    @ikurious 27 дней назад

    Unlisted?

  • @93simongh
    @93simongh 25 дней назад

    I wish you'd also show how to build these in a self hosted, local environment.

    • @themax2go
      @themax2go 21 день назад

      won't do it cuz it'd take away their revenue

  • @datawarrior2023
    @datawarrior2023 22 дня назад +3

    This is great, but showing us things we can't do since not all of us are privileged enough to have access to LangGraph Cloud without even mentioning it isn't available, is not cool.

  • @darkmatter9583
    @darkmatter9583 27 дней назад

    hi