Prompt Engineering Tools
This section contains a list of non-IDE tools that are useful for prompting.
Prompt Development, Testing, and Chaining
LangChain
Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
This library is aimed at assisting in the development of those types of applications.
Dust.tt
The Dust platform helps build large language model applications as a series of prompted calls to external models. It provides an easy to use graphical UI to build chains of prompts, as well as a set of standard blocks and a custom programming language to parse and process language model outputs.
It provides a series of features to make development of applications faster, easier and more robust:
- running multiple completions in parallel
- inspecting execution outputs
- versioning prompt chains
- custom programming language to process data and text
- API integration for various models and external services
OpenPrompt1
Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre-trained tasks. OpenPrompt is a library built upon PyTorch and provides a standard, flexible and extensible framework to deploy the prompt-learning pipeline. OpenPrompt supports loading PLMs directly from huggingface transformers. In the future, we will also support PLMs implemented by other libraries.
BetterPrompt
⚡ Test suite for LLM prompts before pushing them to PROD ⚡
Prompt Engine
NPM utility library for creating and maintaining prompts for Large Language Models (LLMs).
Promptify
Relying solely on LLMs is often insufficient to build applications & tools. To unlock their full potential, it's necessary to integrate LLMs with other sources of computation or knowledge and get the pipeline ready for production.
This library is aimed at assisting in developing a pipeline for using LLMs APIs in production, solving NLP Tasks such as NER, Classification, Question, Answering, Summarization, Text2Graph etc. and providing powerful agents for building chat agents for different tasks.
TextBox2
TextBox 2.0 is an up-to-date text generation library based on Python and PyTorch focusing on building a unified and standardized pipeline for applying pre-trained language models to text generation:
ThoughtSource
"ThoughtSource is a central, open resource and community centered on data and tools for chain-of-thought reasoning in large language models (Wei 2022). Our long-term goal is to enable trustworthy and robust reasoning in advanced AI systems for driving scientific research and medical practice."
Misc.
GPT Index3
GPT Index is a project consisting of a set of data structures designed to make it easier to use large external knowledge bases with LLMs
Deforum
AI animated videos
Visual Prompt Builder
Build prompts, visually
Interactive Composition Explorer
ICE is a Python library and trace visualizer for language model programs.
PTPT - Prompt To Plain Text
PTPT is an command-line tool that allows you to easily convert plain text files using pre-defined prompts with the help of ChatGPT. With PTPT, you can effortlessly create and share prompt formats, making collaboration and customization a breeze. Plus, by subscribing, you gain access to even more prompts to enhance your experience. If you're interested in prompt engineering, you can use PTPT to develop and share your prompts.
Other
- Ding, N., Hu, S., Zhao, W., Chen, Y., Liu, Z., Zheng, H.-T., & Sun, M. (2021). OpenPrompt: An Open-source Framework for Prompt-learning. arXiv Preprint arXiv:2111.01998. ↩
- Tang, T., Junyi, L., Chen, Z., Hu, Y., Yu, Z., Dai, W., Dong, Z., Cheng, X., Wang, Y., Zhao, W., Nie, J., & Wen, J.-R. (2022). TextBox 2.0: A Text Generation Library with Pre-trained Language Models. ↩
- Liu, J. (2022). GPT Index. https://doi.org/10.5281/zenodo.1234 ↩