New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Think about prompt caching #107

Open

hadley opened this issue Oct 9, 2024 · 1 comment

Member

hadley commented Oct 9, 2024 •

edited

Loading

claude: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
gemini: https://ai.google.dev/api/caching
openai: https://platform.openai.com/docs/guides/prompt-caching

Will need to add a third category to tokens to record number of cached input tokens.

hadley mentioned this issue

Consider not saving chat history #130

Closed

Member Author

hadley commented Oct 31, 2024

If caching not support, give a message (and if needed a user can use suppressMessages()
Need to think about how tools get cached too
Especially for gemini where if you change the tools after you have cache the content, the cache will be invalid.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment