Advanced RAG - Self Querying Retrieval

Поделиться
HTML-код
  • Опубликовано: 29 окт 2024

Комментарии • 9

  • @artmusic6937
    @artmusic6937 2 месяца назад

    what if the text you want to query, is so large that you need to chunk it. Will you have then multipe chunks in the database with the same metadata?
    for e.g if you ask your chatbot a question it constructs the query which filters only the relevant chunks, and you end up for example with 10 chunks of the same document wich are then used as context?

  • @Wigglylove
    @Wigglylove 5 месяцев назад

    Why is it called self querying, and not LLM-based query generation?

    • @ivanhelsing214
      @ivanhelsing214 5 месяцев назад

      in contrast to "query expansion", it takes only the metadata from the original ("self") query, and adds nothing. And this can be implemented not only with LLM, in general :D

    • @premp8201
      @premp8201 4 месяца назад

      😊😊Daq😊1😊😊😊êw😊😊😊😊😊😊😊😊😊w😊wqq¹ SD d😊5a😊ar😊😊😊😊😊😊⁵x😊t😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊∆​@@ivanhelsing214

  • @8eck
    @8eck 5 месяцев назад

    This will add an additional LLM call into any query. Which is not so good.

    • @daniel_romero
      @daniel_romero 5 месяцев назад +2

      Thinking about production: using a cheaper LLM or a local SLM is not so bad.

    • @devSero
      @devSero 5 месяцев назад +1

      It's actually good if you design it well. Sometimes you need additional information as LLMs can hallucinate regardless of prompt quality.

    • @ivanhelsing214
      @ivanhelsing214 5 месяцев назад

      @@devSero you can provide a few-shot prompting (which, I think, LangChain already does under the hood)

    • @devSero
      @devSero 5 месяцев назад

      @@ivanhelsing214 I'm aware but I don't use LangChain for production purposes.