sadpandajoe commented on code in PR #44130:
URL: https://github.com/apache/superset/pull/44130#discussion_r4075774029
##########
docs/docs/using-superset/using-ai-with-superset.mdx:
##########
@@ -267,6 +293,15 @@ Ask your admin for the MCP server URL and any
authentication tokens you need.
| `create_virtual_dataset` | Create a virtual dataset from a SQL query
|
| `update_dataset_metric` | Update a saved metric's expression, name,
verbose_name, or format (affects every chart using it; requires dataset
ownership) |
+### Semantic Layer
+
+| Tool | Description
|
+| ---------------------------- |
-----------------------------------------------------------------------------------------------------------------------------------
|
+| `list_metrics` | Discover metrics by name/description across
built-in datasets and external semantic views, with compatible dimensions
included |
+| `get_table` | Query a dataset or semantic view by metric
and dimension names, with optional filters, time range, and sorting
|
+| `get_compatible_dimensions` | Given metrics/dimensions already selected,
return the full set of dimensions compatible with that selection (may include
ones already selected) |
+| `get_compatible_metrics` | Given metrics/dimensions already selected,
return the metrics that can still be added (already-selected metrics excluded)
|
Review Comment:
`get_compatible_metrics` forwards external semantic views’ compatible set
without removing selected metrics. A client that relies on this unconditional
“excluded” promise can offer duplicates; should the docs qualify it or the tool
filter it consistently?
##########
docs/docs/using-superset/using-ai-with-superset.mdx:
##########
@@ -267,6 +293,15 @@ Ask your admin for the MCP server URL and any
authentication tokens you need.
| `create_virtual_dataset` | Create a virtual dataset from a SQL query
|
| `update_dataset_metric` | Update a saved metric's expression, name,
verbose_name, or format (affects every chart using it; requires dataset
ownership) |
+### Semantic Layer
+
+| Tool | Description
|
+| ---------------------------- |
-----------------------------------------------------------------------------------------------------------------------------------
|
+| `list_metrics` | Discover metrics by name/description across
built-in datasets and external semantic views, with compatible dimensions
included |
+| `get_table` | Query a dataset or semantic view by metric
and dimension names, with optional filters, time range, and sorting
|
+| `get_compatible_dimensions` | Given metrics/dimensions already selected,
return the dimensions that can still be added
|
Review Comment:
The table wording is correct now, but the workflow still tells clients to
use both helpers to find choices that can still be added.
`get_compatible_dimensions` still returns selected dimensions on built-in
datasets; could that step distinguish its full set from the metrics delta?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
