We can always do better! Little (or not so little) pessimist in me also want to say "We can also always do worse!"
But do not listen to him! Let's see how we might make this better.
Best code is the one you do not write!
You can actually totally remove Backend service and have client make all the calls, problem is that you will have your API keys exposed and there is no other way to authenticate api calls as of now for Open AI and Eleven Labs.
Cache π΅ because all cool kids are doing it!
Cache! We are making call to fetch our CMS data on each request, this might not be needed as our data for CV does not change often if at all. This can also save costs because in the example I am using Hygrpah which has a free tier but can eventually reach its free quota.
Maybe if we use please word more in our prompt? π€ (do not fail to note sarcasm in the quote)
Better prompting, if you explore LlamaIndex there are ways how one can make their promoting yield better and more accurate responses. You can create custom Prompt template, or make have clear instructions about how system should behave.
Outro π
This was a lot, please feel free to look at the code base and ask any question you might have.
I would also welcome any improvements that one is willing to share.
And lastly, if you make all the way, thank you so much I hope you had some fun and learn something in the process.
β€οΈIf you would like to stay it touch please feel free to connectβ€οΈ
Top comments (0)