# AI-ML on PromQL Query Data Set
Single Prometheus data stream can contain multi-variate time-series data. See the query example,
```
irate(node_cpu_seconds_total{job="node",mode="user"}[5m])&step=2m&duration=12h
```
The query represents a multi-variate data set and is visualized by the line chart. There are 7 time-series data sets specified with the data key "instance". The group-by operator was used for displaying all 7 data sets.
The current Apica Data Fabric (ADF) AI-ML operator supports only one data set. To use the AI-ML on the data, the user needs to filter the data into one data set. The process can be done with the promQL select operator,
```
irate(node_cpu_seconds_total{job="node",mode=~"user", instance=~".*arm8.*"}[5m])&step=2m&duration=12h
```
After filtering into just one data set, one can now use the AL-ML tool to process the dataset. Notice that the "group-by" operator CANNOT be used in the chart configuration.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.apica.io/autonomous-insights/time-series-ai-ml/ai-ml-on-promql-query-data-set.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.