CanvasXpress AI and Guided Autocomplete

CanvasXpress AI: Powered by LLM

CanvasXpress AI is a feature that allows users to interact with their data using large language models (LLMs). This functionality enables you to explore data and create visualizations or code with a single click by simply describing what you want in plain English. You can use provided datasets or upload your own files via drag-and-drop.

Below are examples of how CanvasXpress AI works with different data types and visualizations.

When you describe a chart, the AI writes the spec — a validated CanvasXpress configuration (the meta.cxplot grammar) that you can use as-is or refine. You don't touch code. And because AI edits flow through the same pipeline as manual interactions, every AI-generated change lands in the reproducible audit trail, so the figure still records exactly how it was made.

The copilot is powered by the open-source canvasxpress-mcp server, which turns plain-English requests into validated configs and also exposes the same capability over the Model Context Protocol so external AI agents can build CanvasXpress figures.

Building your own AI tooling? CanvasXpress publishes a machine-readable knowledge base for LLMs at /llms.txt (with the full version at /llms-full.txt), including the minimal parameters, schema, and a working call for every graph type under /data/md/.

Chatting with Data in CanvasXpress

Here are some examples of how to interact with CanvasXpress AI using large language models (LLMs). You can either use the provided datasets or drag and drop your own tab-delimited file into any of the CanvasXpress visualizations (currently shown as data tables for clarity). Simply describe in plain English what you want the visualization to look like, including the column names you want to use.

Examples - Update on a table

• Create a Boxplot of len grouped by supp and dose showing the original data jittered.
• Create a Violin plot of len grouped by supp in a vertical orientation. Rotate the sample labels 90 degrees.
• Create a Bar graph of len color by supp. Orient vertically and show legend on top in two columns.

Examples - Update on a plot

• Create a Scatter plot of cty and hwy color by class.
• Create a Regression plot of cyl and displ.
• Create a Loess fit of cty and hwy color by class.

Examples - Append on a plot

• Create a Scatter plot of mpg and wt.
• Create a Filled contour of mpg and wt.

Guided Autocomplete for CanvasXpress

**Guided Autocomplete for CanvasXpress** is an integrated feature designed to help users create effective prompts for configuring parameters accurately. This functionality was instrumental in generating the few-shot examples required to train our LLM model.

When you use Guided Autocomplete, there is no need to ask the LLM to generate visualizations. Instead, CanvasXpress will generate the configuration parameters needed for the visualizations. If the prompt cannot be validated, CanvasXpress will forward it to the LLM for processing.

Setting up the correct configuration isn't complicated. It's simply about translating the parameters into plain English—there's no need to craft it into poetry.

How it works

Guided Autocomplete can be enabled or disabled using a toggle widget in the chat interface. As you start typing, you'll see a set of initial suggestions for how to begin your new sentence. You can simply press the tab key to accept a suggestion. If there are multiple options available, pressing tab will select the first one in the list.

Initial Suggestions

• Sort data by
• Filter data where
• Group by
• Set the hierarchy to
• Set the Sankey axes to
• Transform the x-axis to
• Transform the y-axis to
• Transform the data to
• Set the maximum value for the x-axis to
• Set the minimum value for the x-axis to
• Set the maximum value for the y-axis to
• Set the minimum value for the y-axis to
• Set the maximum value for the data to
• Set the minimum value for the data to
• Orient the graph
• Use the style
• Use the color scheme
• Set the title for the graph to
• Increase the font size of the graph title
• Decrease the font size of the graph title
• Set the color of the graph title to
• Set the title for the x-axis to
• Increase the font size of the x-axis title
• Decrease the font size of the x-axis title
• Set the color of the x-axis title to
• Increase the font size of the x-axis ticks
• Decrease the font size of the x-axis ticks
• Set the color of the x-axis ticks to
• Set the title for the y-axis to
• Increase the font size of the y-axis title
• Decrease the font size of the y-axis title
• Set the color of the y-axis title to
• Increase the font size of the y-axis ticks
• Decrease the font size of the y-axis ticks
• Set the color of the y-axis ticks to
• Set the title for the samples to
• Increase the font size of the sample title
• Decrease the font size of the sample title
• Set the color of the sample title to
• Increase the font size of the sample labels
• Decrease the font size of the sample labels
• Set the color of the sample labels to
• Set the title for the variables to
• Increase the font size of the variable title
• Decrease the font size of the variable title
• Set the color of the variable title to
• Increase the font size of the variable labels
• Decrease the font size of the variable labels
• Set the color of the variable labels to
• Increase the font size of the sankey title
• Decrease the font size of the sankey title
• Set the color of the sankey title to
• Increase the font size of the sankey labels
• Decrease the font size of the sankey labels
• Set the color of the sankey labels to
• Rotate the sample labels 45 degrees
• Rotate the sample labels 90 degrees
• Rotate the variable labels 45 degrees
• Rotate the variable labels 90 degrees
• Color by
• Shape by
• Size by
• Line by
• Ridge by
• Regression Line by
• Loess Spline by
• Scale the data point size
• Show original data
• Jitter the data
• Bin the data
• Hide the legend
• Show the legend
• Put the legend on the
• Divide the legend in two columns
• Fit the data with a regression line
• Fit the data with a loess spline
• Fit the with a quantile regression line
• Overlay samples data with factor
• Overlay variables data with factor
• Add a red horizontal line at
• Add a red vertical line at
• Add a blue horizontal line at
• Add a blue vertical line at
• Add a black horizontal line at
• Add a black vertical line at
• Set the area graph
• Set the area style
• Join the data points with a
• Hide the whiskers
• Show single whiskers
• Show the inner boxplot in the violin plot
• Do not trim the violin plot
• Position the histogram bars as
• Show the density curve in histogram
• Show the filled density curve in histogram
• Show median line in density plot
• Show histogram bars in density plot
• Set the density curve in density plot to
• Show the quantile lines in ridgeline plot
• Show the density data points in ridgeline plot
• Show filled contour
• Show contourdata points
• Cluster the variables
• Cluster the samples
• Set the bullet target variable to
• Set the bullet range stack to
• Set the R Axis to
• Set the track names to
• Set Venn groups to

Based on the initial suggestion, Guided Autocomplete will propose ways to complete the sentence. Several of these suggestions exhibit a well-defined structured format.

Example of a Structured Suggestion

• Create a **`{graph}`** of **`{column}`** **`{concatenator}`**

When you begin typing your suggestion, guided autocomplete will automatically complete the sentence with the available graph types in CanvasXpress, such as bar graph, line graph, scatter plot, and more. Once you select the graph type, guided autocomplete will add the term 'of' and suggest the columns from your dataset. After you finish typing the first column, guided autocomplete will propose a comma, a period, or 'and' to help you concatenate the entries.