In this video I show how easy is to extend Kernel Memory to use a local Embedding model and a local LLM thanks to Python, Fast Api and LM studio.
The code is here: github.com/alkampfergit/Seman...
▬ Contents of this video ▬▬▬▬▬▬▬▬▬▬
00:00 - Introduction and Overview
00:22 - Customizing the Embedding Part
01:12 - Creating a Server with Python
04:34 - Testing the Model with Postman
06:04 - Integrating Models from Hugging Face into Kernel Memory
08:09 - Creating an External Embedding Generator Class
12:03 - Using Local Embedding for the G Part of the RAG
13:04 - Using LM Studio for Model Search
14:19 - Running the Whole Example Locally
17:59 - Configuration and customization
20:20 - Conclusion and Final Thoughts
29 июл 2024