This package provides an easy and reusable interface to build prompts for Large scale Language Models (LLMs).

Prompt Engineering is a technique used to elicit intended responses out of a LLM model and can work on many strategies.

LLMs like GPT-3 and Codex have continued to push the bounds of what AI is capable of - they can capably generate language and code, but are also capable of emergent behavior like question answering, summarization, classification and dialog. One of the best techniques for enabling specific behavior out of LLMs is called prompt engineering - crafting inputs that coax the model to produce certain kinds of outputs. Few-shot prompting is the discipline of giving examples of inputs and outputs, such that the model has a reference for the type of output you're looking for.

Prompt engineering can be as simple as formatting a question and passing it to the model, but it can also get quite complex - requiring substantial code to manipulate and update strings. This library aims to make that easier. It also aims to codify patterns and practices around prompt engineering.

See How to get Codex to produce the code you want article for an example of the prompt engineering patterns this library codifies.

The library currently supports a generic GenericEngine and a TextAnalysisEngine. Both facilitate a pattern of prompt engineering where the prompt is composed of a description, examples of inputs and outputs and an ongoing "dialog" representing the ongoing input/output pairs as the user and model communicate. The dialog ensures that the model (which is stateless) has the context about what's happened in the conversation so far.

See architecture diagram representation:

The repository includes a few examples, showing how to leverage the library to generate free form text, JSON files such as Azure ARM templates, pseudo code like Mermaid graphs, etc.

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

This library aims to simplify use of Large Language Models, and to make it easy for developers to take advantage of existing patterns. This package works independently of any specific LLM - prompt generated by the package should be usable with various language and code generating models.

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.