OpenAI Embeddings

OpenAI Embeddings can be seamlessly integrated into Lyntaris V2 via the Document Stores (/vector-databases) configuration tab.

Because Lyntaris uses Shared Credentials synchronized from your deployment, there is no requirement to paste raw OpenAI API keys into every embedding node individually.

🏗️ Configuration Protocol

To assign standard OpenAI Embeddings to a Lyntaris Vector Database:

1. Navigate to Vector Databases in the left-hand menu.
2. Select your target Document Store (e.g., Pinecone, Qdrant) and enter the Configure Embeddings step.
3. If not already selected, click Other Embedding Providers and choose OpenAI Embeddings.
4. In the configuration popup, input your specific model details:
   • Model Name: Enter the OpenAI embedding model designation (e.g., text-embedding-3-small or text-embedding-ada-002).

🔑 Shared Credentials (Crucial Step)

The definitive mechanism for V2 architecture is utilizing the proper environment-level credential.

In the Connect Credential dropdown, locate and select the Shared OpenAI credential that has been dynamically populated by the Lyntaris Host.

[!WARNING] DO NOT click "Create New" or manually inject an OpenAI API key unless specifically mandated for a pipeline-scoped override. Always rely on the built-in Shared Credentials.

Resources

• OpenAI Embeddings Documentation
• Lyntaris Credentials Architecture