# fnnx-ai/scikit-llm

Seamlessly integrate LLMs into scikit-learn.

Repository: https://github.com/fnnx-ai/scikit-llm
Canonical: https://ross.abutalabs.com/products/scikit-llm
Homepage: https://beastbyte.ai/
Language: Python
License: MIT
License Family: permissive
Topics: chatgpt, deep-learning, llm, machine-learning, scikit-learn, transformers
Last push: 2026-08-01T01:20:22+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 34, longevity 86
- inputs: {"age_days": 1209, "days_push": 33, "days_rel": 224, "gap_med": 218.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3529, forks 287 (observed 2026-08-28T04:08:08.848070+00:00)

## What it is
Scikit-LLM is a Python library that integrates large language models like GPT into scikit-learn workflows as estimators. It enables tasks such as zero-shot text classification, summarization, and vectorization using familiar fit/predict APIs.

## Use cases
- zero-shot text classification with GPT
- use LLMs inside scikit-learn pipelines
- classify text sentiment without training data
- summarize documents with an LLM estimator
- build ML workflows that mix classical models and LLMs
- label text datasets using large language models

## When to choose
- you already use scikit-learn and want LLM-powered estimators
- you need zero-shot classification or text analysis without training a model
- you want to drop LLMs into existing sklearn pipelines

## When to avoid
- you need high-throughput, low-latency inference without API costs
- you want to fine-tune or train LLMs yourself
- you don't use Python or the scikit-learn ecosystem

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, nlp, llm-inference, data-science
- domain: machine-learning, large-language-models, data-science
- platform: python
- tags: scikit-learn, llm, zero-shot-classification, text-analysis, openai, estimators, natural-language-processing

## Member repositories
- fnnx-ai/scikit-llm (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:08.848070+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 2026-08-29T18:35:08.010674+00:00, confidence not recorded.
  - readme: https://github.com/fnnx-ai/scikit-llm (fetched 2026-08-28T04:08:08.848070+00:00, sha 5edb9d2d6e51)
  - homepage: https://beastbyte.ai/ (fetched 2026-08-29T09:29:02.691421+00:00, sha 1e61b155c0fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.