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
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.
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
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.
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
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
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
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.
Is this grounding option available for Gemini Pro model ? Mine is greyed out.
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
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.
For a datastore that uses website search, you need turn on Enterprise: cloud.google.com/generative-ai-app-builder/docs/enterprise-edition
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
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