Grounding in Vertex AI

แชร์
ฝัง
  • เผยแพร่เมื่อ 4 พ.ย. 2024

ความคิดเห็น • 8

  • @rafaelmagossi137
    @rafaelmagossi137 7 หลายเดือนก่อน +1

    Hi Mark, thank you for the amazing tutorials; they're really good. I'm learning alot. I was wondering, what is the difference between grounding and tuning a base model in Vertex AI? For instance, even when grounded, the prompt for random questions still receives an answer without grounding

    • @markryan2475
      @markryan2475  7 หลายเดือนก่อน +1

      Hi @rafaelmagossi137 - thanks very much for your feedback. I really appreciate it! Good question about tuning vs. grounding. The documentation for tuning cloud.google.com/vertex-ai/generative-ai/docs/models/tune-models states it well - it's designed for specific tasks, and you specify the tuning with JSONL files that give a pattern for input and response that you want the tuned model to follow. By contrast, grounding cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview is for more open-ended use cases where you want queries that may not follow a particular input format to get responses that are grounded in the datastore that you specify. In addition, the data for grounding can be a set of URLs, BQ tables, and content in Cloud Storage. See cloud.google.com/generative-ai-app-builder/docs/create-data-store-es for details.

  • @cboss8
    @cboss8 8 หลายเดือนก่อน +1

    Is this grounding option available for Gemini Pro model ? Mine is greyed out.

    • @markryan2475
      @markryan2475  8 หลายเดือนก่อน

      Hi - thanks for your comment. Right now, text-bison and chat-bison are supported: cloud.google.com/vertex-ai/docs/generative-ai/grounding/ground-language-models#before_you_begin

  • @FaisalA-np3yw
    @FaisalA-np3yw 8 หลายเดือนก่อน

    Hi, I am getting an error
    ERROR. Cannot use enterprise edition features (website search, multi-modal search, extractive answers/segments, etc.) in a standard edition search engine.

    • @markryan2475
      @markryan2475  8 หลายเดือนก่อน

      For a datastore that uses website search, you need turn on Enterprise: cloud.google.com/generative-ai-app-builder/docs/enterprise-edition

  • @jashsureja3801
    @jashsureja3801 9 หลายเดือนก่อน

    I'm getting an error 404 not found for my datastore, can you please help? I have provided the path as shown in the video, projects/project_id/locations/global/collections/default-collection/dataStore/datastore_id,
    I'm getting Error message: "DataStore projects/project_id/locations/global/collections/default-collection/dataStores/datastor_id not found."
    Status: 404 Error code: 404

    • @markryan2475
      @markryan2475  9 หลายเดือนก่อน

      Hi - thanks for your comment. You need to replace "project-id" with the ID of the project that you are using and replace "datastor_id" with the datastore ID shown in Vertex AI Search for your datastore. You can see more details in this Vertex AI documentation topic: cloud.google.com/vertex-ai/docs/generative-ai/grounding/ground-language-models