rank
rank places every line of its input on a scale of levels you name, from lowest to highest, and prints the lines from highest to lowest. --top keeps only the first few.
thinkthen rank --level routine --level urgent \ 'How urgent is the request?' messages.txtOutput
I was charged twice for one invoice.
Where is my parcel?
Please refund my order.
Please refund my order.Where is my parcel?I was charged twice for one invoice.Most urgent first: the double charge, then the parcel question, then the refund request.
Keep the top few
Section titled “Keep the top few”thinkthen rank --level routine --level urgent --top 2 \ 'How urgent is the request?' messages.txtOutput
I was charged twice for one invoice.
Where is my parcel?
--top 2 keeps the two most urgent lines and drops the rest.
See why
Section titled “See why”See why
--json prints the details. This jq keeps three of them for each line.
thinkthen rank --json --level routine --level urgent \ 'How urgent is the request?' messages.txt | jq -c '{position, answer, levels: .detail.levels}'Output
{"position":3,"answer":1,"levels":[0.55,0.45]}
{"position":2,"answer":2,"levels":[0.86,0.14]}
{"position":1,"answer":3,"levels":[0.95,0.05]}
position is the line's place in the input, answer is its rank, and levels holds the chance of each level, lowest first. Lines with equal scores keep their input order. JSON output lists every field.
Rank every row of a CSV file
Section titled “Rank every row of a CSV file”Rank every row of a CSV file
id,texta1,Please refund my order.a2,Where is my parcel?a3,I was charged twice for one invoice.thinkthen rank 'How urgent is the request?' \ --level routine --level urgent --from csv \ --column text --into urgency_rank < messages.csvOutput
id,text,urgency_rank
a1,Please refund my order.,3
a2,Where is my parcel?,2
a3,I was charged twice for one invoice.,1
--column names the column to read, and --into names the new rank column. The rows stay in their order, each with its rank. With --top, a row outside the top gets an empty cell. File types covers TSV, Excel and other files.
Options
Section titled “Options”Options
| Option | What it does |
|---|---|
<QUESTION> | Question to ask |
[FILE]... | Input files; default: standard input |
--name <NAME> | Optional execution identity |
--text <TEXT> | Judge this text instead of reading input |
--level <LEVEL> | Scale level; repeat low to high |
--top <TOP> | Maximum answered ranks |
--column <COLUMN> | Field column; repeat; replaces a saved pointer |
--details [=<DETAILS>] | Add status, probability, error, detail and source columns |
--in-place [=<IN-PLACE>] | Replace source with backup |
--into <INTO> | Answer field for JSON Lines; column for tables |
--output <OUTPUT> | Destination path |
--sheet <SHEET> | Worksheet |
If rank can't answer a line, it prints an error and exits with code 2, 4, 5 or 6. Troubleshooting lists each error and its fix.
In code: Python · TypeScript · Go · Java · Kotlin · C# · R · Ruby · Rust · Swift · Zig · C · C++ · DuckDB · SQLite · PostgreSQL
Next: find points to the line in a text that answers a question.