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

Humanprompt

HumanPrompt is a Python framework for researchers to design, manage, share and use human-readable prompts and prompt-based methods with large language models. It organizes experiments around configurations for datasets, methods and metrics, and supports custom prompt transformations and answer extraction.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Humanprompt — 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 HumanPrompt when structuring an LLM prompt-method experiment around a dataset and metrics, particularly when you need to customize prompt transformation or answer extraction. Consider its deprecated status before starting new work.

Who it is for

  • Researchers testing or comparing prompt-based methods with large language models.
  • Developers extending research workflows with custom prompt transformations or answer extractors.

Documented uses

  • Configure a prompt method against a dataset and selected evaluation metrics.
  • Adapt dataset fields to a shared task interface for a method.
  • Customize prompt construction and answer extraction.
  • Run examples such as Chain-of-Thought on CommonsenseQA or GSM8K, and zero-shot text-to-SQL on Spider.
Before you choose

Requirements & limits

The repository is public and identified as open source. The README documents local installation from a repository clone and uses an OpenAI API key as an example environment variable.

  • The repository explicitly marks HumanPrompt as deprecated and recommends checking LangChain.
  • Experiment configuration covers dataset selection and field mapping, method settings, and metrics.
  • Custom transform and extract classes allow researchers to adapt prompt construction and answer parsing.
  • The documented workflow uses a local Python installation and may require an LLM API key.

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

Set up HumanPrompt for a research experiment

Install the package and prepare the documented experiment configuration workflow.

Before you start

  • A local clone of the HumanPrompt repository
  • Python package installation with pip
  • An LLM API key, such as the OpenAI key shown in the README

Steps

  1. Clone the repository.

  2. From the repository, run the command below to install the package and link the hub directory.

    Documented command
    pip install -e .

  3. Set the relevant environment variable, such as OPENAI_API_KEY.

  4. Create a YAML file under examples/configs/ to specify the dataset, method and metrics.

Expected outcome

The package and hub are installed, and an experiment configuration is prepared for the documented run stage.

Guide limitations

  • The repository marks HumanPrompt as deprecated and recommends checking LangChain.
  • The setup instructions do not by themselves document successful execution of a configured experiment.
Documentation 1 ↗
Evidence and transparency

Sources & review

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

Related options

LangChain — Named in the HumanPrompt repository description as an alternative readers should check because HumanPrompt is deprecated.

Explore project →