Update model hosting details and add Microsoft Foundry#43020
Update model hosting details and add Microsoft Foundry#43020brandonpham13 wants to merge 1 commit intogithub:mainfrom
Conversation
Added Microsoft Foundry as a model hosting provider and updated prompt caching references. Reference: https://azure.microsoft.com/en-us/blog/introducing-anthropics-claude-models-in-microsoft-foundry-bringing-frontier-intelligence-to-azure/ https://ai.azure.com/catalog/publishers/anthropic
|
Thanks for opening this pull request! A GitHub docs team member should be by to give feedback soon. In the meantime, please check out the contributing guidelines. |
github-actions
bot
added
the
triage
How to review these changes 👓Thank you for your contribution. To review these changes, choose one of the following options: A Hubber will need to deploy your changes internally to review. Table of review linksNote: Please update the URL for your staging server or codespace. The table shows the files in the
Key: fpt: Free, Pro, Team; ghec: GitHub Enterprise Cloud; ghes: GitHub Enterprise Server 🤖 This comment is automatically generated. |
There was a problem hiding this comment.
Pull request overview
Updates the {% data variables.product.prodname_copilot %} “Model hosting” reference to reflect Microsoft Foundry as an additional hosting provider for Anthropic models, and extends the provider/privacy and prompt-caching references accordingly.
Changes:
- Added Microsoft Foundry to the list of hosting providers for Anthropic models.
- Added a Microsoft Foundry data/privacy reference alongside existing provider commitments.
- Added a Microsoft Foundry prompt caching reference alongside existing provider documentation links.
| * Amazon Bedrock: Amazon makes the [following data commitments](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html): _Amazon Bedrock doesn't store or log your prompts and completions. Amazon Bedrock doesn't use your prompts and completions to train any AWS models and doesn't distribute them to third parties_. | ||
| * Anthropic PBC: {% data variables.product.github %} maintains a [zero data retention agreement](https://privacy.anthropic.com/en/articles/8956058-i-have-a-zero-retention-agreement-with-anthropic-what-products-does-it-apply-to) with Anthropic. | ||
| * Google Cloud: [Google commits to not training on {% data variables.product.github %} data as part of their service terms](https://cloud.google.com/vertex-ai/generative-ai/docs/data-governance). {% data variables.product.github %} is additionally not subject to prompt logging for abuse monitoring. | ||
| * Microsoft Foundry: [Data, privacy, and security for Azure Direct Models in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy?view=foundry&tabs=azure-portal). |
There was a problem hiding this comment.
The provider list bullets summarize each vendor’s data commitment (e.g., Amazon quote, Anthropic ZDR agreement, Google non-training + no prompt logging), but the new Microsoft Foundry bullet is only a link. To keep this section self-contained and consistent, add a brief summary of Microsoft’s relevant commitments (for example: whether prompts/completions are stored/logged and whether they’re used for training), and keep the link as the supporting reference.
| * Microsoft Foundry: [Data, privacy, and security for Azure Direct Models in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy?view=foundry&tabs=azure-portal). | |
| * Microsoft Foundry: For Azure Direct Models, Microsoft states that your inputs and outputs are not used to train Microsoft or third-party models and are retained only for limited periods for abuse monitoring and service operations. For more information, see [Data, privacy, and security for Azure Direct Models in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy?view=foundry&tabs=azure-portal). |
1 participant
Why:
Closes: #43019
What's being changed (if available, include any code snippets, screenshots, or gifs):
Model hosting page of the GitHub Copilot docs.
Added Microsoft Foundry as a model hosting provider, included data privacy agreement, updated prompt caching references.
Reference: https://azure.microsoft.com/en-us/blog/introducing-anthropics-claude-models-in-microsoft-foundry-bringing-frontier-intelligence-to-azure/
https://ai.azure.com/catalog/publishers/anthropic
Check off the following: