> ## Documentation Index > Fetch the complete documentation index at: https://private-7c7dfe99-mintlify-8c05c8a2.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Text-to-Chart > Generate charts from natural language prompts in ClickStack using the AI-powered Text-to-Chart feature. export const Image = ({img, alt, size}) => { return {alt}

; }; ClickStack's Text-to-Chart feature allows you to create visualizations by describing what you want to see in plain text. Rather than manually selecting metrics, filters, and group-by fields, you can type a prompt such as "error rates by service over the last 24 hours" and ClickStack will generate the corresponding chart automatically. This feature uses a large language model (LLM) to convert your text prompt into a query, then builds the visualization in the [Chart Explorer](/clickstack/features/dashboards/overview#navigate-chart-explorer). It works with any configured data source.

Prerequisites

Text-to-Chart requires an [Anthropic API key](https://console.anthropic.com/). Set the `ANTHROPIC_API_KEY` environment variable when starting ClickStack. For open source deployments, pass the key as an environment variable. The method varies by deployment type: ```bash theme={null} docker run -e ANTHROPIC_API_KEY='' -p 8080:8080 -p 4317:4317 -p 4318:4318 clickhouse/clickstack-all-in-one:latest ``` ```bash theme={null} docker run -e ANTHROPIC_API_KEY='' -p 8080:8080 docker.hyperdx.io/hyperdx/hyperdx-local ``` Add the variable to your `.env` file or set it directly in the `docker-compose.yaml`: ```yaml theme={null} services: app: environment: ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY} ``` Pass the key using `--set`: ```bash theme={null} helm install my-hyperdx hyperdx/hdx-oss-v2 \ --set env[0].name=ANTHROPIC_API_KEY \ --set env[0].value= ```

Using Text-to-Chart

Navigate to Chart Explorer

Select **Chart Explorer** from the left menu in HyperDX.

Select a data source

Choose the data source you want to visualize — for example, **Logs**, **Traces**, or **Metrics**. Chart explorer

Enter a text prompt

At the top of the Chart Explorer, locate the **AI Assistant** input. Type a natural language description of the chart you want to create. For example: * `Show error rates by service over the last 24 hours` * `Latency breakdown by endpoint` * `Count of events over time grouped by severity` ClickStack converts the prompt into a query and renders the visualization automatically. Text to chart

Trying it with demo data

The quickest way to try Text-to-Chart is with the [Local Mode](/clickstack/deployment/local-mode-only) Docker image and the [remote demo dataset](/clickstack/example-datasets/remote-demo-data): ```bash theme={null} docker run -e ANTHROPIC_API_KEY='' -p 8080:8080 clickhouse/clickstack-local:latest ``` Navigate to `localhost:8080`. To connect to demo data, go to **Team Settings** and create a new connection with the following details: * **Connection Name**: `Demo` * **Host**: `https://sql-clickhouse.clickhouse.com` * **Username**: `otel_demo` * **Password**: Leave empty Create connection

Then modify each of the sources — **Logs**, **Traces**, **Metrics**, and **Sessions** — to use the `otel_v2` database. For full details on configuring sources, see the [remote demo dataset guide](/clickstack/example-datasets/remote-demo-data). Once connected, open the **Chart Explorer** and try prompts against the available logs, traces, and metrics.

Example prompts

The following prompts demonstrate common use cases when working with observability data: | Prompt | Data source | Description | | ------------------------------------------------- | ----------- | ---------------------------------------------- | | `Error count by service over time` | Logs | Charts the frequency of errors across services | | `Average request duration grouped by endpoint` | Traces | Shows latency patterns per endpoint | | `P99 latency by service` | Traces | Identifies tail latency across services | | `Count of 5xx status codes over the last 6 hours` | Logs | Tracks server error trends | Prompts can reference any column or attribute available in your configured data sources. The more specific the prompt, the more accurate the generated chart.

Limitations

* Text-to-Chart currently supports Anthropic as the LLM provider. Support for additional providers, including OpenAI, is planned for future releases. * Only logs and traces are supported as data sources. Prometheus metrics are not yet supported. * Chart accuracy depends on the clarity of the prompt and the structure of the underlying data. If a generated chart does not match expectations, try rephrasing the prompt or specifying column names explicitly.