Python functions that answer questions about text

Pass a string or a list. Read the answer from Call.value.

Install

Channel
`pip install thinkthen`
`uv add thinkthen`

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 thinkthen as tt

question = "Does the customer ask for a refund?"

broken = "Please refund my order. It arrived broken."
is_refund = tt.decide(question, broken).value
assert is_refund is True

refund = tt.question(decide=question, threshold=(0.2, 0.8))
send_back = "I want to send this back."
is_refund = tt.decide(refund, send_back).value
assert is_refund is None

reports = [
    (
        "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).value
assert triage == [
    {"steps": True, "area": "export", "impact": 1.99},
    {"steps": True, "area": "login", "impact": 2.0},
    {"steps": False, "area": "billing", "impact": 0.01},
]

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

To apply one question to a list or a stream, read Functional patterns.

Run facts

Call.facts counts this call.

Errors

Every failure raises a ThinkThenError. Its subclass names the kind: UsageError, BackendError, LocalError, DeadlineError, DefectError or Cancelled.

Settings and recording

tt.Engine takes each setting as a keyword and reads the environment for the rest. record= writes a recording to a folder. replay= answers from that recording with no connection. The Settings page lists every setting.

Jev, Liquid d1 and Ollama from Python

Python reads its backend from the environment. Set THINKTHEN_BACKEND to the name below. Set the backend's key variable in the shell, and the same sample asks that backend.

Backend	Name	Key variable
TypeSafe Jev	`typesafe`	`TYPESAFE_API_KEY`
Liquid d1	`liquid`	`LIQUIDAI_API_KEY`, then `LIQUID_API_KEY`
Ollama	`ollama`	`OLLAMA_API_KEY`. A local address needs no key.

Ask TypeSafe Jev.

export THINKTHEN_BACKEND=typesafe
export TYPESAFE_API_KEY=...

Ask Liquid d1.

export THINKTHEN_BACKEND=liquid
export LIQUIDAI_API_KEY=...

Ask Ollama. This block names a second port, 11535, as the site's runs do. On the default port, leave THINKTHEN_BASE_URL out.

export THINKTHEN_BACKEND=ollama
export THINKTHEN_BASE_URL=http://localhost:11535/v1

import thinkthen as tt

question = "Does the customer ask for a refund?"
broken = "Please refund my order. It arrived broken."
thanks = "Thanks for the quick help yesterday!"
broken_is_refund = tt.decide(question, broken).value
thanks_is_refund = tt.decide(question, thanks).value
assert broken_is_refund is True
assert thanks_is_refund is False

The configuration file's backend names a default backend for every run. The Configuration page shows the file.

OpenAI Decisions API from Python

OpenAI announced its Decisions API on 2026-09-29 in its DevDay 2026 recap. OpenAI has published no address, schema or price, so ThinkThen cannot call it. The OpenAI Decisions API page says what ThinkThen knows.

What is different in Python

A list goes in and Call.value holds the answered list. The list crosses into the engine once.
tt.question() builds a question that carries its own threshold. Reuse it wherever you ask.

On GitHub: github.com/botassembly/thinkthen