Скачать или смотреть SemantiCache: Easy-to-use Semantic Caching Library for LLM Apps | LangChain | Hugging Face | FAISS

In this video, we walk through a live demo of SemantiCache, a python library I developed to simplify semantic caching for LLM apps to only a few lines of code!

It is platform and model agnostic, will work for almost any type of implementation. Can be used as the caching layer for LLM API service or even a simple Streamlit app as demonstrated in this video.

The SematiCache library utilizes LangChain, Hugging Face and FAISS under the hood.

▶ Python Package → https://pypi.org/project/SemantiCache...
▶ Code Repo → https://github.com/theabrahamaudu/Sem...

Like, Share & Subscribe!

---------------------------------------------
Timestamps:
00:00 Intro
01:23 Homepage & Docs
04:38 Live Demo
14:05 Advanced Configurations
16:20 GitHub Repo
18:48 Outro

---------------------------------------------
Connect with me:
▶ GitHub → https://github.com/theabrahamaudu
▶ X (formerly Twitter) → https://x.com/the_abrahamaudu
▶ LinkedIn →   / theabrahamaudu  
▶ Instagram →   / the_abrahamaudu