Polars functions that answer questions about text

A Polars frame goes in. Read the frame with its new columns from Call.value.

Install

Channel
`pip install thinkthen[polars]`

Set THINKTHEN_API_KEY in the environment.

A first call

form.json, a file the sample reads

{
  "version": 1,
  "questions": {
    "steps": {
      "decide": "Does the report give steps to reproduce?"
    },
    "area": {
      "choose": "Which part of the app is this?",
      "options": [
        "export",
        "login",
        "billing"
      ]
    },
    "impact": {
      "score": "How much does this block the user?",
      "levels": [
        "None.",
        "Slows them.",
        "Blocks work."
      ]
    }
  }
}

import polars as pl
import thinkthen as tt

reports = pl.DataFrame({
    "body": [
        (
            "CSV export fails every time. "
            "Steps: open a report,\n"
            "click Export, pick CSV. "
            "My month-end numbers are stuck.\n"
        ),
        (
            "Steps: open the login page, enter a password, "
            "press Enter. The page spins and "
            "nobody can sign in."
        ),
        (
            "The Pay button on the billing page "
            "is a slightly "
            "different blue. No steps, I just noticed it."
        ),
    ],
})
triage = tt.annotate("form.json", reports, on="body").value
assert triage.select("steps", "area", "impact").rows() == [
    (True, "export", 1.99),
    (True, "login", 2.0),
    (False, "billing", 0.01),
]
assert triage["failed"].to_list() == [None, None, None]

Not sure comes back as None. Branch on it and send those cases to a person. Each function page shows its Polars call.

Run facts

Call.facts counts the whole frame call. The new columns hold only the answers.

Errors

Every failure raises a ThinkThenError, as in Python. A failed row in a column call ends the call with BackendError.

Settings and recording

tt.Engine takes each setting as a keyword, as in Python. record= writes a recording to a folder. replay= answers from that recording with no connection. The Settings page lists every setting.

Backends

Polars runs on the Python engine, so it reaches each backend the same way. The Python page shows Jev, Liquid d1 and Ollama.

What is different in Polars

decide, choose, score, and tag send a whole column to the engine in one call.
on= names the column the questions read.

On GitHub: github.com/botassembly/thinkthen