Vikram Oberoi
Vikram Oberoi
**Is your feature request related to a problem? Please describe.** Anthropic's models regularly have control characters in their strings, producing invalid JSON that causes validation to fail. **Describe the solution...
Instructor doesn't expose an easy way to see or use the raw arguments that Instructor finally sends over to a language model: #907, #767, https://github.com/jxnl/instructor/issues/888#issuecomment-2262366959) This PR is a sketch...
Is there prompt caching support? I couldn't find evidence in the docs. If not, would love to have that baked in.