Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/microsoft/promptpex below:

microsoft/promptpex: Test Generation for Prompts

Test Generation for Prompts

• Read the documentation
• PromptPex technical paper

Prompts are an important part of any software project that incorporates the power of AI models. As a result, tools to help developers create and maintain effective prompts are increasingly important.

PromptPex provides the following capabilities:

• It will automatically extract output rules that are expressed in natural language in the prompt. An example of a rule might be "The output should be formatted as JSON".
• From the rules, it will generate unit test cases specifically designed to determine if the prompt, for a given model, correctly follows the rule.
• Given a set of rules and tests, PromptPex will evaluate the performance of the prompt on any given model. For example, a user can determine if a set of unit tests succeeds on gpt-4o-mini but fails on phi3.
• PromptPex uses an LLM to automatically determine whether model outputs meet the specified requirements.
• Automatically export the generated tests and rule-based evaluations to the OpenAI Evals API.

• GitHub Models Extension

The PromptPex tool runs dockerized with this command.

docker run -p 8003:8003 ghcr.io/microsoft/promptpex:v0

Please reference responsible-ai-transparency-note.md for more information.

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 opencode@microsoft.com with any additional questions or comments.

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.

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4