This PR introduces support for PGVector as a feature in the vectorstore, and extends functionality to Azure China and Azure Global for both PGVector and Redis Stack.

ruoccofabrizio / azure-open-ai-embeddings-qna

A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.

MIT License

846 stars 510 forks source link

Changes Made

PGVector Support:
- Added PGVector as a supported feature in the vectorstore.
- Implemented necessary changes to ensure compatibility and proper integration.
Azure China and Azure Global Support:
- Extended support for PGVector to Azure China and Azure Global environments.
- Added functionality to enable PGVector and Redis Stack in these environments.

Motivation and Context

This PR addresses the need for PGVector support in the vectorstore and the requirement to expand compatibility to Azure China and Azure Global. The inclusion of PGVector enhances the capabilities of the vectorstore, and the extended support for Azure regions allows for broader usage.

How to Test

Deploy the modified code to a test environment.
Verify that PGVector is functioning as expected in the vectorstore.
Test the functionality of PGVector and Redis Stack in both Azure China and Azure Global environments.