Stephan Janssen
Stephan Janssen
Keep in mind that Gemini also has prompt caching, so any design should work for both! Google Gemini cache documentation @ https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-create
The cache with Anthropic is only valid for 5 minutes, not sure about Gemini. Auto re-populating the cache when expired would probably be a nice (advanced) feature?
Some extra info about the two prompt caches 
⚠️ Claude Sonnet 3.5 feedback (hopefully this helps?) : "Based on your observations, it seems there may be some optimization opportunities for llama3.java on Apple Silicon platforms. Let's analyze this...
We'll need to modify several components of the existing codebase. Here's a step-by-step approach to implement this feature: 1. Create a Conversation model 2. Modify the ChatMemoryService to store multiple...
To implement a conversation history view similar to the one shown in the image, we'll need to modify the DevoxxGenieToolWindowContent class and create a new panel for displaying recent conversations....
I'm taking this one... 😜
https://github.com/user-attachments/assets/22aab533-1306-4a6b-a386-71bc6680d30f