Master RAG on Vertex AI with Vector Search and Gemini Pro

Поділитися
Вставка

КОМЕНТАРІ • 31

  • @IanMcAleer-op1xj
    @IanMcAleer-op1xj 5 місяців тому

    Thanks, this is tremendously helpful
    One point to note - you need to upload the embed file, not the sentence file -> upload_file(bucket_name,embed_file_path)

  • @edubr2011
    @edubr2011 8 місяців тому +3

    Excelent video! Thanks for sharing the code too.

  • @ScottJohnson-d3x
    @ScottJohnson-d3x 3 місяці тому

    Very excellent Learning session Janakiram!

  • @sureshkumarselvaraj8911
    @sureshkumarselvaraj8911 7 місяців тому +1

    Great video! What is the difference between Vertex Search service VS Vector Search for RAG application? which one is better in terms of handling better retrieval of relevant documents for RAG application where we deal with 100+ PDF documents? Can you share some insights?

  • @jagatmohansarvari5681
    @jagatmohansarvari5681 4 місяці тому

    really helpful for understanding the concept of embedding and retrieval. Thanks.

  • @thecopt11
    @thecopt11 7 місяців тому +2

    Best tutorial. Big thanks for your shared.

  • @tinkutoysadda5767
    @tinkutoysadda5767 12 днів тому

    Hi Janaki Ram garu
    Can we use for developers javascript we have provide previous code embedding store data use case generate unit test cases send to gen ai llm. Please suggest which model Rag or longchain using vector search or chroma ?
    Which is low cost

  • @Ahsan_Akhtar1
    @Ahsan_Akhtar1 3 місяці тому

    really helpful I have question i have multiple pdf files how i handel with them?

  • @MarceloFerreira-rl6hh
    @MarceloFerreira-rl6hh 6 місяців тому

    Great job! Thanks a lot. What’s the difference between this approach and using langchain?

  • @jmpresto
    @jmpresto День тому

    Where can I get a copy of this notebook ?

  • @AhmedBesbes
    @AhmedBesbes 7 місяців тому

    Thanks for the tutorial!
    Instead of going through the ids in the json file to fetch the sentences, is it possible to integrate those directly as metadata in the index?

  • @Hitish99999
    @Hitish99999 7 місяців тому

    Thanks for the tutorial. I am bit confused which file to be uploaded to bucket. sentence file or embedding file

  • @ShahidGhetiwala-dg3ol
    @ShahidGhetiwala-dg3ol 7 місяців тому +1

    Great Video, thank you soo much........

  • @JulianHarris
    @JulianHarris 8 місяців тому +1

    Nice. Are you ok to share the colab notebook?

    • @Janakirammsv
      @Janakirammsv  8 місяців тому

      Yes, sure. Please check the description. I have added the links.

  • @TomFord-mv2mx
    @TomFord-mv2mx 7 місяців тому

    Great Video. One question, I noticed you used a different model (gecko) to Gemini Pro for the embeddings. Is this ok to do? I assumed the models needed to be the same for both training and inference? Thanks again

    • @Janakirammsv
      @Janakirammsv  7 місяців тому +1

      Text embedding models are independent of LLMs. You only have to ensure that the same embedding model is used for indexing the documents and the query. This is critical to retrieving the context based on the similarity.

  • @digiplouxinc.6688
    @digiplouxinc.6688 3 місяці тому

    In your video you say "sentence_file_path". However shouldn't it be "embed_file_path" ? create_tree_ah_index function should have the GCS bucket of the embedded data and not the text with teh ids right ?

  • @dhananjaypathak15
    @dhananjaypathak15 4 місяці тому

    i want same thing in nodej can some one please help on which library to use

  • @wanderlust8367
    @wanderlust8367 5 місяців тому

    the code link u have shared is incomplete, load_file is missing and other few stuffs,

  • @yadusingh8701
    @yadusingh8701 16 днів тому

    Nice Video

  • @GAURAVRAUT007
    @GAURAVRAUT007 6 місяців тому

    Excellent video - can u please do same with Langchain with retrieval

  • @tarunrey619
    @tarunrey619 8 місяців тому

    Thanks for sharing knowledge.
    Can you share the notebook

    • @Janakirammsv
      @Janakirammsv  8 місяців тому

      Please check the description. I have added the links.

  • @LearnAiWithVikas
    @LearnAiWithVikas 7 місяців тому +1

    Can you please do a video on "How to use the same in Langchain with retrieval"

  • @AlaGalai-m9l
    @AlaGalai-m9l 7 місяців тому

    why always python is there any way to use js?

  • @khondakersajid1138
    @khondakersajid1138 8 місяців тому

    Possible to share the notebook?

    • @Janakirammsv
      @Janakirammsv  8 місяців тому

      The code is available at gist.github.com/janakiramm/55d2d8ec5d14dd45c7e9127d81cdafcd and gist.github.com/janakiramm/7dd73e83c92a0de0c683ed27072cdde2

  • @arvindmathur6574
    @arvindmathur6574 7 місяців тому +1

    Great!