embedded.dotnet.markdown

Connection String to bge-micro-v2 (Embedded)

---

{NOTE: }

• This article explains how to define a connection string to the bge-micro-v2 model.
  This model, designed exclusively for embeddings generation, is embedded within RavenDB, enabling RavenDB to seamlessly handle its embeddings generation tasks without requiring an external AI service.

• Running the model locally consumes processor resources and will impact RavenDB's overall performance,
  depending on your workload and usage patterns.

• In this article:

  • Define the connection string - from the Studio
  • Define the connection string - from the Client API
  • Syntax

{NOTE/}

---

{PANEL: Define the connection string - from the Studio}

1. Name
   Enter a name for this connection string.

2. Identifier (optional)
   Learn more about the identifier in the connection string identifier section.

3. Connector
   Select Embedded (bge-micro-v2) from the dropdown menu.

4. Click Save to store the connection string or Cancel to discard changes.

{PANEL/}

{PANEL: Define the connection string - from the Client API}

{CODE:csharp create_connection_string_embedded@AiIntegration\ConnectionStrings\connectionStrings.cs /}

{PANEL/}

{PANEL: Syntax}

{CODE:csharp embedded_settings@AiIntegration\ConnectionStrings\connectionStrings.cs /}

{PANEL/}

Related Articles

Vector Search

• RavenDB as a vector database
• Vector search using a static index
• Vector search using a dynamic query

Embeddings Generation

• Generating embeddings - overview
• Embeddings generation task

AI Connection Strings

• Connection strings - overview