mirascope
mirascope copied to clipboard
Mirascope
LLM abstractions that aren't obstructions
Advanced tutorial for creating Advanced web agent with sources
### Description When using liteLLM with OpenAI models, cost and token usage tracking do not work on all calls. Calls that takes more than 2 secondes don't report either usage...
Hey there! This is very much WIP, but I thought it would be easier to talk about implementation here. I had to re-remember how to do write tests with mocks,...
### Description Can we create some kind of interface which simulates COT kind of thinking. Currently for Groq we have [g1](https://github.com/bklieger-groq/g1). Can we provide something which can help people to...
### Description > This is blocked until they actually release the model We already have audio support for Gemini, we should add support for the upcoming `gpt-4o-audio-preview` release 1. Get...
### Description We should include documentation specifically around best practices to deploy apps built using Mirascope to production. This should cover things like error handling, retries, and more. For anyone...
### Description > Inspired by #342 to show how Mirascope supports this functionality without the abstraction of a graph It would be beneficial to show how to implement the same...
### Description Recently Google released Structured Outputs for Gemini (much like OpenAI). Should be fairly simple to enable this by updating `setup_call` for `gemini` and updating the warning to include...