Skill

Implement Retrieval-Augmented Generation

Semantic Kernel RAG skill demonstrates retrieval-augmented generation patterns using vector collections and self-critique techniques for Python AI applications.

Maintainer of this project? Claim this page to edit the listing.


91
Spark score
out of 100
Updated 5 months ago
Version 1.0.0

Add to Favorites

Why it matters

Leverage Retrieval-Augmented Generation (RAG) patterns with Semantic Kernel to enhance AI responses by grounding them in external knowledge sources. This asset provides examples for building more informed and accurate AI applications.

Outcomes

What it gets done

01

Implement RAG with vector collections.

02

Develop self-critique RAG patterns.

03

Integrate external data for generation.

04

Build more accurate AI response systems.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/sk-concept-rag | bash

Overview

Semantic Kernel - Rag

This skill provides two Python examples demonstrating retrieval-augmented generation patterns with Semantic Kernel. The `rag_with_vector_collection.py` file shows how to retrieve context from vector stores before generating responses. The `self_critique_rag.py` file implements a pattern where the AI evaluates and refines its own RAG-based outputs. Use this skill when you need to connect language models to your own knowledge bases, documents, or data repositories. It's ideal for building AI applications that must cite sources, reduce hallucinations, or provide answers grounded in specific domain knowledge rather than relying solely on pre-trained model knowledge.

What it does

When you need to ground AI responses in your own data sources, this skill helps you implement retrieval-augmented generation (RAG) patterns with Semantic Kernel. It gets the concrete job done by providing two working examples: rag_with_vector_collection.py shows how to retrieve relevant context from vector stores before generation, and self_critique_rag.py demonstrates a pattern where the AI critiques and refines its own RAG outputs. You can adapt these patterns to connect language models to your knowledge bases, documents, or proprietary data.

Source README

Retrieval-augmented generation patterns with Semantic Kernel

Examples (2 files):

  • rag_with_vector_collection.py
  • self_critique_rag.py

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.