mirror of
https://github.com/marcominerva/SqlDatabaseVectorSearch.git
synced 2026-06-20 12:23:10 +00:00
Marco Minerva
dcccdf7365
- Updated README.md with details on Vector Support in Azure SQL Database, application functionalities, and setup instructions. - Removed inheritance of `Question` class from `Search` class and deleted `Search` class. - Minor adjustment in Program.cs for endpoint description consistency. - Simplified appsettings.Development.json by removing the empty "ConnectionStrings" section. - Enhanced Script.sql with SQL commands to create `DocumentChunks` and `Documents` tables, including schema for identifiers, content, embeddings, document names, creation dates, and established a foreign key relationship between the two tables.
SQL Database Vector Search Sample
A repository that showcases the Vector Support in Azure SQL Database to perform embeddings and RAG with Azure OpenAI.
Important
Usage of this application requires the Vector Support feature in Azure SQL Database, currently in EAP. See this blog post for more details.
The application is a Minimal API that exposes endpoints to load documents, generate embeddings and save them into the database as Vectors, and perform searches using Vector Search and RAG. Database access is done using the EFCore.SqlServer.VectorSearch library.
Setup
- Create an Azure SQL Database on a server that has the Vector Support feature enabled.
- Execute the Scripts.sql file to create the tables needed by the application.
- Open the appsettings.json file and set the connection string to the database and the other settings required by Azure OpenAI.