Upgrade to Pro — share decks privately, control downloads, hide ads and more …

LangChain Japan Meetup

LangChain Japan Meetup

Hiroki YAMAMOTO

July 20, 2023
Tweet

More Decks by Hiroki YAMAMOTO

Other Decks in Technology

Transcript

  1. LangChain Japan MeetUp
    @Mercari, Inc., Roppongi
    2023/07/20
    Hiroki YAMAMOTO
    New Bubiness Dep., Classmethod, Inc.

    View Slide

  2. 2
    About me
    Hiroki YAMAMOTO
    @Classmethod, Inc.
    May 2020~
    ・R&D team of Computer Vision
    ・Skeleton Detection
    ・Person Tracking
    March 2023~
    ・researching LLM
    My blog posts
    ・https://dev.classmethod.jp/author/yamamoto-hiroki/

    View Slide

  3. 3
    About Classmethod, Inc. (クラスメソッド株式会社)
    Main business
    ・AWS (SI Partners of the Year 2022)
    Company blog
    ・DeveloperIO (over 40,000 posts)
    Focusing on LLM
    ・OpenAI 632 posts
    ・ChatGPT 349 posts
    (as of July 17)
    Hiring!
    ・https://careers.classmethod.jp/requirements/nb-llm-engineer/
    start consulting service
    press release (March 16 2023)
    service for multi GAIs and
    secure connection
    press release (July 7 2023)

    View Slide

  4. 4
    We are utilizing LangChain (Thank you!)
    Session presentations @ devio2023 (more than 500 attendees)
    Also using on the back-end side
    De-Blackboxing! Thorough explanation
    of LangChain and LlamaIndex used with
    LLM.
    Extending ChatGPT‘s functionality with
    LangChain ~How to generate natural
    responses by leveraging past
    conversations and Google search
    results~

    View Slide

  5. 5
    My Interest
    Agent・Tool(Function Calling)
    ・I tried with Zapier NLA (March 17 2023)
    → Awesome
    AI can have arms and legs! Zapier
    Natural Language Actions + LangChain
    is amazing, so I tried it
    decompose task and call tools

    View Slide

  6. 6
    My Job (I’m researching)
    QA Chatbot
    ・RAG (Retrieval Augumented Generation) = LangChain Indexes
    I created a bot that uses OpenAI's API
    to perform vector searches of sales
    materials
    I tried "except" and "large and small
    numbers" in the vector search and it
    looked difficult
    I've been trying to figure out the
    problem and how to improve it when a
    vector search doesn't give me the
    information I want

    View Slide

  7. 7
    How to improve

    View Slide

  8. 8
    I’m trying
    Function Calling
    ・(via LangChain Agent)
    Experiment
    ・about
    ・Numerical Comparison
    ・Tool Selection
    ・perspective
    ・Cost・Performance
    ・GPT3.5 vs GPT4
    I checked the conditions under which
    a function is called in Function calling
    of OpenAI API

    View Slide

  9. 9
    My Opinion (I'm searching for / finding / looking forward to)
    new type of LLM specialized for Agent (will come / change the world)
    ・very smart (logical, comprehensive, thoughtful)
    ・not need so much knowledge
    ・low cost, low latency (for iterative thinking = API call)
    ・can control tens of tools
    hierarchical structured tools/agents for more accurate task processing
    ・like human organizational structure
    ・each tool may include agent (and human as a tool)

    View Slide