Skill

Answer Questions Using Your Own Data

Name: Answer Questions Using Your Own Data
Availability: OnlineOnly
Author: Semantic Kernel

Three Python examples demonstrating retrieval-augmented generation (RAG) with Azure OpenAI On Your Data, covering API usage, function calling, and vector

Get skill

Works with azure openai

Semantic Kernel

Maintainer?

Spark score

out of 100

Updated 3 months ago

Version 1.0.0

Models

gpt 4o

Add to Favorites

Why it matters

Leverage your private documents and data to power intelligent conversations and gain insights. This asset enables retrieval-augmented generation (RAG) with Azure OpenAI, allowing you to query your data using natural language.

Outcomes

What it gets done

Index your data for efficient retrieval.

Generate responses based on your specific information.

Integrate with Azure OpenAI for advanced language capabilities.

Build conversational interfaces that understand your context.

Install

Add it to your toolbox

Run in your project directory:

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

Capabilities

What this skill does

RAG index

Chunks, embeds, and indexes documents for semantic retrieval.

Summarize

Condenses long documents or threads into key takeaways.

Query a database

Writes and executes SQL or NoSQL queries on databases.

Chatbot

Handles multi-turn conversations within a defined domain.

Overview

Semantic Kernel - On Your Data

What it does

Three Python code examples demonstrating different approaches to using Azure OpenAI On Your Data for retrieval-augmented generation

How it connects

When you need working code examples for implementing RAG with Azure OpenAI On Your Data using API calls, function calling, or vector search

Source README

Retrieval-augmented generation (RAG) with Azure OpenAI On Your Data

Examples (3 files):

azure_chat_gpt_with_data_api.py
azure_chat_gpt_with_data_api_function_calling.py
azure_chat_gpt_with_data_api_vector_search.py

Discussion