# promptslab/Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

Repository: https://github.com/promptslab/Promptify
Canonical: https://ross.abutalabs.com/products/promptify
Homepage: https://discord.gg/m88xfYMbK6
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chatgpt, chatgpt-api, gpt-3, gpt-3-prompts, prompt-engineering, prompt-toolkit, prompting, chatgpt-python, gpt3-library, openai, prompt-tuning, prompts, large-language-models, transformers, machine-learning, nlp, gpt-4, gpt-4-api, prompt-versioning, promptversioning
Last push: 2026-03-27T01:09:45+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 35, longevity 97
- inputs: {"age_days": 1360, "days_push": 160, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4635, forks 363 (observed 2026-08-28T04:08:55.417982+00:00)

## What it is
Promptify is a Python library that turns LLMs into task-based NLP engines, providing high-level APIs for NER, classification, QA, and custom tasks with Pydantic-validated structured outputs. It uses LiteLLM as a universal backend so any prompt-based model (GPT-4, etc.) can be swapped in, and includes built-in evaluation metrics.

## Use cases
- extract named entities from medical text with an LLM
- classify text sentiment into custom labels using GPT
- get structured JSON answers from a language model
- run question answering over documents with evidence and confidence
- define custom NLP tasks with Pydantic schemas
- evaluate LLM prompt outputs with metrics
- swap between OpenAI and other LLM providers without code changes

## When to choose
- you want scikit-learn-style task APIs (NER, classify, QA) on top of LLMs
- you need validated, structured output rather than free-form text
- you want provider-agnostic LLM access via LiteLLM
- you need built-in evaluation for prompt-based NLP tasks

## When to avoid
- you need raw low-level control over prompts and completions
- you want fine-tuning or training of models rather than inference
- you need non-Python environments
- you want a fully local NLP pipeline without LLM API calls

## Facets
- artifact type: library
- maturity: active
- function: nlp, prompt-engineering, llm-inference, serialization
- domain: large-language-models, machine-learning, artificial-intelligence
- platform: python
- tags: structured-output, pydantic, ner, text-classification, question-answering, litellm, openai, natural-language-processing

## Member repositories
- promptslab/Promptify (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:55.417982+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 2026-08-29T18:19:34.608228+00:00, confidence not recorded.
  - readme: https://github.com/promptslab/Promptify (fetched 2026-08-28T04:08:55.417982+00:00, sha 97b08a7826cf)
  - homepage: https://discord.gg/m88xfYMbK6 (fetched 2026-08-29T09:04:16.263013+00:00, sha a230d7af2237)
  - registry_pypi: https://pypi.org/pypi/promptify/json (fetched 2026-08-29T09:04:16.283444+00:00, sha 97264370b4b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.