Documentationbreadcrumb arrow Grafana Cloudbreadcrumb arrow AI and machine learningbreadcrumb arrow Grafana Assistantbreadcrumb arrow Guidesbreadcrumb arrow Query data
Grafana Cloud

Query data

Grafana Assistant can help you write, explain, and optimize queries across your observability stack. Whether you need PromQL for metrics, LogQL for logs, TraceQL for traces, or SQL for business data, the Assistant can generate valid syntax and visualize the results.

The Assistant can query the following data sources:

  • Metrics - Prometheus, (Grafana Cloud and on-premise endpoints), InfluxDB
  • Logs - Loki data sources
  • Traces - Tempo for distributed tracing
  • Profiles - Pyroscope (via Grafana Cloud Profiles)
  • Load Testing - k6 Cloud results
  • SQL Databases - PostgreSQL, MySQL, ClickHouse, BigQuery, Athena
  • External APIs - Infinity datasource for querying web APIs with JSON endpoints

Before you begin

  • Connect data sources: Ensure your data sources (Prometheus, Loki, Tempo, SQL, etc.) are connected.
  • Reference data sources: Use the @ symbol to mention specific data sources in your prompt (for example, @prometheus-ds), ensuring the Assistant queries the correct data.

Metrics (PromQL)

Generate PromQL queries to analyze metrics without memorizing functions and operators.

Draft a query

Describe the metric and aggregation you need.

Create a PromQL query in @prometheus-ds that shows p95 latency for checkout_service over the last hour.

Refine

Ask for variations or filters.

Group by region and sort by highest error rate.

Visualize

Request a visualization in the chat or add it to a dashboard.

Show this as a time series graph.

Logs (LogQL)

Find log patterns and extract insights using LogQL.

Warning

Querying Loki with the Assistant contributes to the Assistant fair-usage policy.

During public preview, we recommend not running wide scans on Loki to avoid exhausting your fair-usage limits.

Search logs

Describe the log stream and filters.

Find logs from @loki-logs where job=“checkout” and level=“error” in the last 15 minutes.

Parse and aggregate

Extract fields and count occurrences.

Parse the JSON payload and show the top five error codes.

Traces (TraceQL)

Locate specific traces to debug latency or errors.

Find traces

Specify the service and conditions.

Query @tempo-traces for traces longer than 2 seconds.

Analyze

Ask for summaries of the findings.

Show the slowest spans and include their service names.

SQL Databases

Query relational databases for business or operational data.

Discover tables

Ask the Assistant to find relevant tables.

Find tables in @orders-database that track checkout failures.

Generate SQL

Describe your question in plain English.

Query for failed checkouts per minute grouped by payment_provider.

External APIs using Infinity data source

Query data from external web APIs and JSON endpoints. The Infinity data source turns any JSON API into a Grafana data source, opening up endless visualization possibilities.

Control which APIs can be queried

The Infinity data source has an allowedHosts setting that controls which URLs the Assistant can query and whether user approval is required.

  • With allowedHosts configured: The Assistant can only query URLs that match the allowed hosts list, but does so automatically without requiring approval for each request.
  • Without allowedHosts configured: The Assistant can query any URL, but will prompt you to approve each request before executing it.

To configure allowed hosts, edit your Infinity data source settings and add the URLs or domains you want to allow. For example, adding https://api.example.com restricts the Assistant to querying endpoints under that domain. For more information, refer to the Infinity data source documentation.

Query a JSON endpoint

Describe the URL and what data you want to retrieve.

Query the API at https://api.example.com/metrics and show me the results.

Transform with jq

Use jq expressions to filter or reshape the response data.

Query https://api.example.com/data and extract only the items where status is “active”.

Visualize as time series

Request time-based visualization for data with timestamps.

Query the API and show the values over time as a graph.

Optimize queries

The Assistant can review and improve your existing queries for performance and accuracy.

Paste your query

Provide the query you want to optimize and tell the Assistant what to do.

Review this PromQL query for performance: sum(rate(http_requests_total[5m]))

Ask for improvements

Ask for specific changes.

Remove high-cardinality labels.

Next steps