OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Promptify

Promptify is a Python library for building task-based NLP workflows with language models, Pydantic structured outputs, LiteLLM as a model backend and built-in evaluation support.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Promptify — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Promptify when building Python applications that need reusable task-based NLP calls with structured results, or when you want evaluation support for prompt-based outputs.

Who it is for

  • Python developers creating LLM-backed NLP utilities or application workflows.
  • Teams that need structured extraction, classification, question answering or evaluation of prompt-based outputs.

Documented uses

  • Extract named entities from text using a specified domain context.
  • Classify text into supplied labels, including multilabel classification.
  • Answer questions from text and return answer-related fields.
  • Create custom NLP tasks whose outputs follow a Pydantic schema.
  • Evaluate task outputs against labeled data using documented metrics.
Before you choose

Requirements & limits

The repository specifies Python 3.9 or later and pip installation; the project is licensed under Apache-2.0.

  • Promptify is a library integrated into developer code, not a hosted workflow described in the repository.
  • Evaluation metrics support requires installing the eval package extra.
  • LiteLLM provides the documented backend abstraction; provider-specific capabilities may vary.
  • The repository documents synchronous, asynchronous and batch-processing patterns.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Promptify with pip

Install the Promptify Python library in a Python 3.9+ environment.

Before you start

  • Python 3.9 or later

Steps

  1. Install the library with the command below.

    Documented command
    pip install promptify

  2. For evaluation metrics support, install the evaluation extra with the command below.

    Documented command
    pip install promptify[eval]

Expected outcome

Promptify is installed, with evaluation metrics support included when the extra is selected.

Guide limitations

  • The installation instructions do not document provider credentials or configuration.
  • Evaluation metrics support requires the optional eval extra.
Documentation 1 ↗
Source-based practical guide

Extract named entities from text

Use Promptify's NER task to return structured entities from text.

Before you start

  • Promptify installed in a Python 3.9+ environment.
  • A model identifier, as shown with gpt-4o-mini in the example.

Steps

  1. Import NER from promptify.

  2. Create an NER task with a model identifier and, if relevant, a domain such as medical.

  3. Call the task with the text to analyze and read the structured NERResult.

Expected outcome

The example returns entities with text and labels, such as age, condition, and symptom.

Guide limitations

  • The README provides an example but does not document provider credentials or model-specific setup.
  • The displayed output is an example, not a guarantee of results for other inputs.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
promptslab/Promptify · Official homepage title · retained in its source language
How we review sourcesSuggest a correction