Overview
Module Details | |
| Core or GitHub Module | Core |
| Restart Required | No |
| Steps Exposed | Yes |
| Step Location | AI > LiteLLM |
| Settings Location | Settings > LiteLLM Settings |
| Prerequisites |
|
The LiteLLM Module enables Users to connect to a self-hosted LiteLLM proxy and access models from 100+ providers through a single configuration. This gives Users one place to manage provider credentials, track spend, and switch models without reconfiguring Decisions.
Configuration/Properties
Installation
- To set up the Module in Decisions, navigate to Settings > Administration > Features, locate the LiteLLM Module, and select Install.
- The AI Common Module will automatically install in the background if this is the first AI Module installed in the environment.
Creating a Dependency:
- After installing the module, navigate to the project that will utilize LiteLLM.
- Then, within the Project, navigate to Manage > Configuration > Dependencies.
- Select Manage, navigate to Modules, and select Decisions.AI.LiteLLM.
- Select Confirm to save the change.
For more information on installing Modules, please visit Installing Modules in Decisions.
For more information about creating a project dependency for a Module, please visit Adding Modules as a Project Dependency
Available Steps
The table below provides a list of all the steps within the module.
| Step Name | Description |
|---|---|
| Create Embeddings | The step allows Users to generate text embeddings. |
| Get Model List | This step returns a list of Models from the connected LiteLLM account. (Configured in LiteLLM settings). |
| Prompt AI | This step enables Users to input Model and AI Prompt information to output a Chat Response. |