4.1 Manage LLM Connector

Define and manage Large Language Model (LLM) provider configurations used by MicroTx Workflows for AI-related workflow and agent operations.

An LLM connector stores the common configuration required to access an LLM provider, including provider type, API connection details, and supported model names. You can define the connector once and reference it from workflow tasks, AI agent profiles, and other AI-driven workflow features instead of repeating provider configuration in each place. LLM connectors support both chat or completion model providers and embedding model providers. Supported provider types include:

• OCI
• Ollama
• OpenAI
• OpenAI-compatible providers
• Oracle Database

For example, you can create an LLM connector for an OpenAI-compatible endpoint, an OCI Generative AI model, an Ollama-hosted model, or an Oracle Database embedding model. After the connector is created, workflows and agents can reference it by name when they need to perform AI operations such as generation, reasoning, tool use, or embedding generation.

• Create an LLM Definition
  Create an LLM connector to define the model provider, model names, and connection details used by the AI features for MicroTx Workflows. You can reference the connector from workflow tasks, AI agent profiles, and other AI-driven workflow configurations.
• Update an LLM Definition
  
• Test an LLM Definition
  
• View an LLM Definition
  
• Delete an LLM Definition