Langchain: The BEST Library For Building AI Apps In Python?

Поділитися
Вставка
  • Опубліковано 8 лют 2025

КОМЕНТАРІ • 10

  • @Python_paratha
    @Python_paratha 8 місяців тому +3

    Your explanation are simple and precise, it's great that that explaining what exactly this code is doing instead of writing the code line by line .

    • @pixegami
      @pixegami  8 місяців тому

      Thank you! Glad you enjoyed it :)

  • @luisjoseve
    @luisjoseve Рік тому +2

    Awesome explanation, thank you very much.

    • @pixegami
      @pixegami  Рік тому

      Thanks! I hope it was helpful.

  • @ĀRYAN_GENE
    @ĀRYAN_GENE Рік тому +1

    LLM : libmagic library gave me the most pain when i was on a project.
    Its like everything was failing and falling apart.

  • @UserHuge
    @UserHuge Рік тому

    How do RAG and function calling combine?

    • @pixegami
      @pixegami  Рік тому

      If you have a deterministic sequence (e.g. RAG first, then use the results and call a function), then you can create a chain: python.langchain.com/docs/modules/chains/
      If you need the AI to reason about which action to take next (e.g. RAG or function calling) then use an Agent, and add "RAG" and "function calling" as tools: python.langchain.com/docs/modules/agents/tools/

  • @astronemir
    @astronemir Рік тому +1

    Why would langchain just reinvent .() chaining? Abusing the python syntax like this. Just return and take in self to enable it using classes, or use a functional pattern.
    I’m disgusted, lol.

    • @pixegami
      @pixegami  11 місяців тому

      I guess you're referring to the LCEL for chaining the expressions? I don't like how it works either. It uses fewer lines/words, but it really does feel a lot less intuitive to parse than just standard function chaining.