llmGateway

Version

Syntax

llmGateway:
'$ref': <string>
apiKey: <string>
chatCompletions: {}
claude: {}
google: {}
jdbcAiApiUsageStore: {}
openai: {}
policies: {}
simpleStore: {}
systemPrompt: {}
llmGateway:
  '$ref': <string>
  apiKey: <string>
  chatCompletions: {}
  claude: {}
  google: {}
  jdbcAiApiUsageStore: {}
  openai: {}
  policies: {}
  simpleStore: {}
  systemPrompt: {}

Attributes

NameRequiredDefaultDescriptionExamples
$reffalse-Reference a component defined under components.-
apiKeyfalse-API key for the LLM provider. Specify here the API key from OpenAI or Anthropic.-

Child Structure

ElementCardinalityDescription
chatCompletions0..1OpenAI Chat Completions API compatible provider. Can be used for the following providers:
claude0..1(Experimental) Anthroic Claude provider configuration Use to configure a LLM gateway to use the anthropic API
google0..1(Experimental)Google AI provider configuration Use to configure a LLM gateway to use the Google LLM API
jdbcAiApiUsageStore0..1Stores AI API usage in a database (experimental).
openai0..1OpenAI provider configuration Use to configure a LLM gateway to use the OpenAI API
policies0..1LLM Gateway policies for token usage and model restrictions.
simpleStore0..1Simple store for the LLM Gateway that stores limits in memory. Users and keys can be configured in the configuration file.
systemPrompt0..1When used with older chat completions API the instruction is converted to a system message like: "system": "You are a helpful assistant."

Can be used in