Settings

Click Settings in the navigation pane for the following settings:
- System
- Services
- API Keys
- Tools
- Budgets

System

CTERA recommends keeping the default values unless CTERA support recommends different values.
Ingest Workers – The number of ingestor workers for scaling. The more workers the faster the ingestion but the more GPU will be used. The workers are similar in concept to threads.
Embedding Mode – The embedding mode breaks down words to numerical values that can be tokenized. The embedding mode is used to convert the numerical values in to a matrix for semantic context. Select the embedding mode to use from the drop-down list. The port must be open. See Inbound Ports.

Note

Using the Open AI embedding mode consumes a lot of tokens. CTERA recommends using Infinity or if you have your own model, use Ollama.

Embedding Model – The way the embedding is generating the text. Choose the embedding model to use from the drop-down list but CTERA recommends not changing the embedding mode if you use the Infinity embedding mode.
Embedding Service URL – The URL for the embedding mode.
Sparse Embedding Model – The sparse embedding model to use from the drop-down list.
FastEmbedService URL – The fast embed service URL. The port must be open. See Inbound Ports.
Default Model – The LLM that will be used as the default, from the LLMs defined to CTERA Content Services.
Classification Model – The LLM model to use for data classification. If enabled, select the model from the drop-down list of LLMs defined to CTERA Content Services.
Summarize Model – The LLM to use to create summaries. .
Vision-Language Model (VLM) – The model to use for the VLM. If enabled, select the model from the drop-down list of LLMs defined to CTERA Content Services.
Personalized Chat Memory – Save chat prompts across the user conversations.

Services

Guardrails Enabled – Guardrails, defined in SecuritySecurity are enabled by default.
Guardrails API Base URL – The address where the guardrails APIs are located.
Guardrails Timeout (ms) – The timeout.

API Keys

To create personal API keys for your account:

Click Generate New Key.
The Generate New API Key Window is displayed.
Enter a key name and scope.
Select the expiration for the API key from the list or Custom to specify a specific number of days.
Click Generate.

Tools

The API keys for specific tools used by Content Services.

Budgets

For future use.