CSV

Parsing and stringifying of Comma Separated Values (CSV) data.

The parsers map CSV data to an array of objects with field names mapping the header. For example, the CSV data:

name, value
A, 10
B, 2
C, 3

maps to the following array of objects:

[
    {
        "name": "A",
        "value": 10
    },
    {
        "name": "B",
        "value": 2
    },
    {
        "name": "C",
        "value": 3
    }
]

def

The def function automatically parses and stringifies CSV data to a Markdown table (it also works for XLSX).

def("DATA", env.files[0])

def also supports basic row filtering options that control how many rows you want to insert in the prompt.

def("DATA", env.files[0], {
    sliceHead: 50, // take first 50
    sliceTail: 25, // take last 25
    sliceSample: 5, // take 5 at random
})

CSV

Similarly to the JSON class in JavaScript, the CSV class provides methods to parse and stringify comma-separated values (CSV) data.

parse

The parse method converts a CSV string into an array of objects. The first row is used as the header row.

const csv = await workspace.readText("penguins.csv")
const rows = CSV.parse(csv)

If the CSV file does not have a header row, you can specify the column names as an array of strings. You can also specify a custom data separator.

const rows = CSV.parse(csv, {
    delimiter: "|",
    headers: ["name", "value"],
})

You can use defData to serialize the rows object to the prompt. defData also supports basic row filtering options like def.

defData("DATA", rows)

Note

The def function works with files, while defData works with live objects.

stringify

The stringify method converts an array of objects to a CSV string.

const csvString = CSV.stringify(rows)

markdownify

The markdownify method converts an array of objects into a markdown table. This encoding is more efficient with LLM tokenizers.

const md = CSV.markdownify(rows)

| name | value |
|------|-------|
| A    | 10    |
| B    | 2     |
| C    | 3     |

parsers

The parsers also provide a parser for CSV. Returns undefined for invalid inputs. It supports files and parsing options.

const rows = parsers.CSV(env.files[0])

Repair

You can specify the repair: true option to fix common LLM mistakes around CSV.

const rows = CSV.parse(csv, { repair: true })