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

Showing content from https://help.github.com/en/github-models/use-github-models/storing-prompts-in-github-repositories below:

Storing prompts in GitHub repositories

Store prompts directly in your GitHub repositories to leverage automated text summarization and other AI-driven functionalities.

Prompts can be stored as files directly within GitHub repositories. This unlocks the ability to view your prompts in an organized UI, share them with non-technical stakeholders, and run seamless iterations and comparisons on adjustments to models and prompts.

• Easy integration with the new suite of AI development tools directly on GitHub.
• Simple and scalable from simple to complex use cases.
• Uses a widely supported format, compatible with existing tools.

Store prompts in YAML files.

The file can be located anywhere in your repository, but must have the extension .prompt.yml or .prompt.yaml.

Example:

name: Text Summarizer
description: Summarizes input text concisely
model: gpt-4o-mini
modelParameters:
  temperature: 0.5
messages:
  - role: system
    content: You are a text summarizer. Your only job is to summarize text given to you.
  - role: user
    content: |
      Summarize the given text, beginning with "Summary -":
      <text>
      {{input}}
      </text>
testData:
  - input: |
      The quick brown fox jumped over the lazy dog.
      The dog was too tired to react.
    expected: Summary - A fox jumped over a lazy, unresponsive dog.
evaluators:
  - name: Output should start with 'Summary -'
    string:
      startsWith: 'Summary -'

name: Text Summarizer
description: Summarizes input text concisely
model: gpt-4o-mini
modelParameters:
  temperature: 0.5
messages:
  - role: system
    content: You are a text summarizer. Your only job is to summarize text given to you.
  - role: user
    content: |
      Summarize the given text, beginning with "Summary -":
      <text>
      {{input}}
      </text>
testData:
  - input: |
      The quick brown fox jumped over the lazy dog.
      The dog was too tired to react.
    expected: Summary - A fox jumped over a lazy, unresponsive dog.
evaluators:
  - name: Output should start with 'Summary -'
    string:
      startsWith: 'Summary -'

Prompts have two key parts:

• Runtime information (required)
  • Prompt templates (system, user, etc.) using simple {{variable}} placeholders
• Development information (optional)
  • Human-readable name and description
  • Model identifier and parameters
  • Sample data for testing and evaluations
  • Data describing the evaluators themselves

You cannot store prompts for:

• Complex templating languages
• Proprietary or complex file formats (such as .ghprompt, or .prompty)

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