# machinalis/quepy

A python framework to transform natural language questions to queries in a database query language.

Repository: https://github.com/machinalis/quepy
Canonical: https://ross.abutalabs.com/products/quepy
Language: Python
License: NOASSERTION
License Family: other
Last push: 2020-12-29T19:38:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 5021, "days_push": 2073, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1264, forks 290 (observed 2026-08-28T04:04:10.804637+00:00)

## What it is
Quepy is a Python framework that transforms natural language questions into database queries, currently supporting SPARQL and MQL. It uses special regular expressions and semantic relations so developers can build natural language interfaces to databases with little code.

## Use cases
- convert natural language questions to SPARQL queries
- build a natural language interface to a knowledge base like DBpedia
- generate MQL queries from English questions
- map question patterns to semantic database queries using regexes
- query RDF endpoints by asking questions in plain English

## When to choose
- you need a rule-based, customizable NL-to-query pipeline without training data
- your target query language is SPARQL or MQL
- you want a lightweight Python framework for natural language database access

## When to avoid
- you need modern neural or LLM-based question answering
- you require query languages other than SPARQL or MQL
- you need actively maintained software with recent updates

## Facets
- artifact type: framework
- maturity: maintenance
- function: nlp, parser, search-engine, database
- domain: databases
- platform: python, cross-platform
- tags: sparql, mql, question-answering, semantic-web, dbpedia, natural-language-to-query, natural-language-processing, search

## Member repositories
- machinalis/quepy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:10.804637+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:03.476146+00:00, confidence not recorded.
  - readme: https://github.com/machinalis/quepy (fetched 2026-08-28T04:04:10.804637+00:00, sha 15f87d6b1233)
  - registry_pypi: https://pypi.org/pypi/quepy/json (fetched 2026-08-29T12:16:17.958962+00:00, sha f51e6f487904)
- Data as of 2026-08-30T08:39:29.467469+00:00.