Simple OpenAI Library with Caching

Cache-as-a-service for generative AI app developement & prod

Last night, while trying to figure out the best way to implement caching in my app, I had an idea for a dirt-simple caching system based on a dependency graph. The premise I started with is that one of the hardest things to manage in a cache is dependencies between entities. In order to cache items effectively, you inevitably have to duplicate "child" data inside of "parent" entries. Then, when a child is changed, you have to invalidate the child and its parents, and its parents' parents, and so on. To try to help this, I hacked together a simple Node.js library called Stash, which models…

Quickly experiment with state-of-the-art ML models

Analyze your OpenAI API usage and logs in real-time

Hey, OpenAI recently released "assistants" - These have RAG built into the API, which means that you can provide up to 10.000 files to the assistant without the overhead of dealing with vector databases, splitting files into chunks and more. They work surprisingly well, so I've built a free simple tool to embed them on websites. It has no dependencies and simply uses fetch to communicate to my backend which proxies openai. In the future I plan to add more widget embedding options (currently only chat is available). Let me know if you have any specific questions about either the tool or…

Threw this little application together today. It uses the OpenAI API to help you figure out what you want to cook next! Please note that the OpenAI API response times are really slow - sorry about that! If someone has suggestions on how I can improve the prompt response time, please share!