LLM JSON Output with Instructor RAG and WizardLM-2

With Instructor library you can implement simple RAG without Vector DB or dependencies to other LLM libraries. The key RAG components - good data pre-processing and cleaning, powerful local LLM (such as WizardLM-2, Nous Hermes 2 PRO or Llama3) and Ollama or MLX backend.

Sparrow GitHub repo:
https://github.com/katanaml/sparrow

0:00 Intro
1:05 Instructor and Unstructured
2:29 Example
3:13 Sparrow Config
4:15 RAG Code
5:00 Data pre-processing with Unstructured
6:15 Sparrow Dynamic response class
6:28 Instructor RAG
8:11 Summary

CONNECT:
- Subscribe …

backend cleaning components data dependencies github github repo good intro json key libraries library llama3 llm mlx nous nous hermes ollama pre-processing processing rag simple the key vector