diff --git a/_docs/master/ai/metabot.md b/_docs/master/ai/metabot.md index 690acc8ab0..5db8fef7fb 100644 --- a/_docs/master/ai/metabot.md +++ b/_docs/master/ai/metabot.md @@ -53,6 +53,7 @@ Some tips: - Whenever you want Metabot to do something completely different, you should reset the conversation, as Metabot might find that irrelevant historical context to be confusing. - Once Metabot creates a question for you, you can follow up with more questions or take over yourself. You can drill through the chart or step into the editor to tweak the query (both in the query builder and the SQL editor). - Metabot works best with English prompts. While it might understand other languages, you'll get the most reliable results by asking your questions in English. +- Define domain-specific terms in the [glossary](../exploration-and-organization/data-model-reference#glossary) to help Metabot understand your organization's terminology. ### Metabot response menu diff --git a/_docs/master/ai/settings.md b/_docs/master/ai/settings.md index 60244d6437..b280489899 100644 --- a/_docs/master/ai/settings.md +++ b/_docs/master/ai/settings.md @@ -48,6 +48,7 @@ The best thing you can do to improve Metabot's performance is to prep your data - [Add models and metrics to your Metabot collection](#add-models-and-metrics-to-your-metabot-collection) - [Add descriptions for your data and content](#add-descriptions-for-your-data-and-content) - [Make sure the semantic types for each field are correct](#make-sure-the-semantic-types-for-each-field-are-correct) +- [Define domain-specific terms in the glossary](#define-domain-specific-terms-in-the-glossary) - [Curate prompt suggestions](#curate-prompt-suggestions) ### Add models and metrics to your Metabot collection @@ -76,6 +77,12 @@ Make sure the semantic types for each field accurately describe the field's "mea Metabase will try to set semantic types automatically, but you should confirm that each field has the relevant semantic type. See [Data types and semantic types](../data-modeling/semantic-types). You can also set semantic types for [models](../data-modeling/models#add-metadata-to-columns-in-a-model). +### Define domain-specific terms in the glossary + +Add your organization's terminology, acronyms, and business-specific terms to the [glossary](../exploration-and-organization/data-model-reference#glossary). When Metabot receives a prompt, it can look up terms in the glossary to better understand your request. + +For example, if you define "MRR" as "Monthly Recurring Revenue" in your glossary, Metabot will know what you mean when you ask "What's our MRR for Q4?" This is especially helpful for industry-specific jargon, internal product names, or abbreviations unique to your organization. + ### Curate prompt suggestions When you select a collection for Metabot to "learn", Metabot will suggest a series of prompts based on the content it finds in that collection. These prompts just give people a feel for the kinds of things people can ask Metabot to do. diff --git a/_docs/master/data-modeling/models.md b/_docs/master/data-modeling/models.md index 160ea878cf..e87d15fa55 100644 --- a/_docs/master/data-modeling/models.md +++ b/_docs/master/data-modeling/models.md @@ -126,7 +126,7 @@ There are some limitations to this indexing: You can edit a model's query by clicking on the down arrow next to the model's name and clicking on **Edit query definition**. When you're doing editing, be sure to save your changes. Unlike questions, which prompt you to save as a new question, any changes here will overwrite the existing model. If you want to create a new model from an existing model, select **Duplicate this model** from the model sidebar (the icon of two overlapping squares). -### Checking for for breaking changes +### Checking for breaking changes > {% include plans-blockquote.html feature="Checking for breaking changes" %} diff --git a/_docs/master/exploration-and-organization/data-model-reference.md b/_docs/master/exploration-and-organization/data-model-reference.md index 3a048fb5b6..b5cc3b5321 100644 --- a/_docs/master/exploration-and-organization/data-model-reference.md +++ b/_docs/master/exploration-and-organization/data-model-reference.md @@ -56,9 +56,9 @@ Admins can edit the metadata in this reference by clicking the **Edit** button i ## Glossary -The glossary is a place where anyone can define terms relevant to your data. Currently, the glossary is a simple key-value store of terms and their definitions. +The glossary is a place where anyone can define terms relevant to your data. To add a new term, click **+ New term**. Add the term name and its definitions, then click the checkmark to save the term to the glossary. -To add a new term, click **+ New term**. Add the term name and its definitions, then click the checkmark to save the term to the glossary. +The glossary is particularly useful for [Metabot](../ai/metabot). When Metabot gets a prompt, it can look up glossary terms to understand your request. For example, if you define "MRR" as "Monthly Recurring Revenue" in your glossary, Metabot will know what you mean when you ask "What's our MRR for Q4?" ## Segments diff --git a/_docs/master/questions/introduction.md b/_docs/master/questions/introduction.md index d8b5bebc2c..4baf244feb 100644 --- a/_docs/master/questions/introduction.md +++ b/_docs/master/questions/introduction.md @@ -61,7 +61,7 @@ Questions that live in a dashboard are only visible in that dashboard. These que Questions saved to a collection can be added to multiple dashboards. Moving a question from one collection to another collection won't have any effect on the dashboards the question has been added to. To save a question to a collection, you'll need to be in a group with [curate access](../permissions/collections#curate-access) to that collection. -### Checking for for breaking changes +### Checking for breaking changes > {% include plans-blockquote.html feature="Checking for breaking changes" %} diff --git a/_site/docs/master/ai/metabot.html b/_site/docs/master/ai/metabot.html index c2cf167f82..20b7a13152 100644 --- a/_site/docs/master/ai/metabot.html +++ b/_site/docs/master/ai/metabot.html @@ -4959,6 +4959,7 @@

The Metabot chat sidebar

  • Whenever you want Metabot to do something completely different, you should reset the conversation, as Metabot might find that irrelevant historical context to be confusing.
  • Once Metabot creates a question for you, you can follow up with more questions or take over yourself. You can drill through the chart or step into the editor to tweak the query (both in the query builder and the SQL editor).
  • Metabot works best with English prompts. While it might understand other languages, you’ll get the most reliable results by asking your questions in English.
    • +
  • Define domain-specific terms in the glossary to help Metabot understand your organization’s terminology.

    • Metabot response menu

    diff --git a/_site/docs/master/ai/settings.html b/_site/docs/master/ai/settings.html index 16b5ae66a2..5b16b1cc20 100644 --- a/_site/docs/master/ai/settings.html +++ b/_site/docs/master/ai/settings.html @@ -4952,6 +4952,7 @@

    Tips for making the most of Metabot
  • Add models and metrics to your Metabot collection
  • Add descriptions for your data and content
  • Make sure the semantic types for each field are correct
    • +
  • Define domain-specific terms in the glossary
  • Curate prompt suggestions
    • @@ -4980,6 +4981,12 @@

    Make sure the s

    Metabase will try to set semantic types automatically, but you should confirm that each field has the relevant semantic type. See Data types and semantic types. You can also set semantic types for models.

    +

    Define domain-specific terms in the glossary

    + +

    Add your organization’s terminology, acronyms, and business-specific terms to the glossary. When Metabot receives a prompt, it can look up terms in the glossary to better understand your request.

    + +

    For example, if you define “MRR” as “Monthly Recurring Revenue” in your glossary, Metabot will know what you mean when you ask “What’s our MRR for Q4?” This is especially helpful for industry-specific jargon, internal product names, or abbreviations unique to your organization.

    +

    Curate prompt suggestions

    When you select a collection for Metabot to “learn”, Metabot will suggest a series of prompts based on the content it finds in that collection. These prompts just give people a feel for the kinds of things people can ask Metabot to do.

    diff --git a/_site/docs/master/data-modeling/models.html b/_site/docs/master/data-modeling/models.html index dbca13c4fd..85a2ed880e 100644 --- a/_site/docs/master/data-modeling/models.html +++ b/_site/docs/master/data-modeling/models.html @@ -5037,7 +5037,7 @@

    Edit a model’s query

    You can edit a model’s query by clicking on the down arrow next to the model’s name and clicking on Edit query definition. When you’re doing editing, be sure to save your changes. Unlike questions, which prompt you to save as a new question, any changes here will overwrite the existing model. If you want to create a new model from an existing model, select Duplicate this model from the model sidebar (the icon of two overlapping squares).

    -

    Checking for for breaking changes

    +

    Checking for breaking changes

    diff --git a/_site/docs/master/exploration-and-organization/data-model-reference.html b/_site/docs/master/exploration-and-organization/data-model-reference.html index d69736b74a..1706ce3cd9 100644 --- a/_site/docs/master/exploration-and-organization/data-model-reference.html +++ b/_site/docs/master/exploration-and-organization/data-model-reference.html @@ -4955,9 +4955,9 @@

    Database details

    Glossary

    -

    The glossary is a place where anyone can define terms relevant to your data. Currently, the glossary is a simple key-value store of terms and their definitions.

    +

    The glossary is a place where anyone can define terms relevant to your data. To add a new term, click + New term. Add the term name and its definitions, then click the checkmark to save the term to the glossary.

    -

    To add a new term, click + New term. Add the term name and its definitions, then click the checkmark to save the term to the glossary.

    +

    The glossary is particularly useful for Metabot. When Metabot gets a prompt, it can look up glossary terms to understand your request. For example, if you define “MRR” as “Monthly Recurring Revenue” in your glossary, Metabot will know what you mean when you ask “What’s our MRR for Q4?”

    Segments

    diff --git a/_site/docs/master/questions/introduction.html b/_site/docs/master/questions/introduction.html index 79c6257cdc..65d75b85af 100644 --- a/_site/docs/master/questions/introduction.html +++ b/_site/docs/master/questions/introduction.html @@ -4955,7 +4955,7 @@

    Saving questions to collections

    Questions saved to a collection can be added to multiple dashboards. Moving a question from one collection to another collection won’t have any effect on the dashboards the question has been added to. To save a question to a collection, you’ll need to be in a group with curate access to that collection.

    -

    Checking for for breaking changes

    +

    Checking for breaking changes