C3 AI Documentation Home

LLM Service Package Documentation

Point any C3 or Nexus consumer at the llmService gateway and call models through one OpenAI-compatible endpoint and virtual key, instead of wiring each application to a provider directly. Administrators register the available models and provider credentials once; consumers then pick a model and call it. Usage, spend, and request traces are visible in one place, and new provider models become available without a platform upgrade. Use it whenever an application or agent must call an LLM or an embedding model.

Dependencies

Dependent PackagePurpose of this Package
nexusBaseBase CloudService, app-start hooks, and shared utilities.

Key types in this package

TypeWhat you use it for
LlmServiceEntry point for the centralized LLM service.
LiteLlmProxy.CloudServiceThe OpenAI-compatible gateway your consumers call.
LiteLlmProxy.ModelRegistryRegister and list the models the gateway exposes.
LiteLlmProxy.CredentialRegistryRegister the provider credentials that back the virtual keys.
LaminarCloudServiceObservability service for traces, metrics, and logs of LLM calls.

Key files in this package

The package is structured in the following manner:

Text
.
└── llmService/
    ├── config
    ├── metadata
    ├── resource
    ├── seed
    ├── test
    └── src/
        └── litellm
Folder nameContent
configPackage configuration files.
metadataSeed roles and package metadata.
resourceRuntime resources such as packaged Helm charts.
seedSeed data for initializing the service (models, providers).
testTests per runtime for the proxy and observability types.
src/litellmLiteLLM proxy CloudService, model registry, credential registry, and clients.
Was this page helpful?