Skip to main content

​
PromptSnapshotConfig

Model provider and settings configuration for prompt deployments.

​
Overview

The PromptSnapshotConfig type defines the model provider, model name, and runtime settings for a deployed prompt snapshot. All fields are optional because a deployment snapshot may have an incomplete configuration.

​
PromptSnapshotConfig

interface PromptSnapshotConfig {
  providerName?: string;
  providerId?: string;
  model?: string;
  settings?: any;
}
Properties:
  • providerName - Provider name in lowercase (e.g., ‘openai’, ‘anthropic’, ‘google’)
  • providerId - Adaline internal provider UUID
  • model - Model name as defined in the provider’s API (e.g., ‘gpt-4o’, ‘claude-3-opus’)
  • settings - Runtime configuration settings passed to the model provider, flexible key-value pairs

​
Examples

​
Basic Configuration

import type { PromptSnapshotConfig } from '@adaline/api';

const config: PromptSnapshotConfig = {
  providerName: 'openai',
  providerId: 'provider_abc123',
  model: 'gpt-4o',
  settings: {
    temperature: 0.7,
    maxTokens: 1000,
    topP: 0.9
  }
};

​
Same parameters across different LLM Providers

// Adaline transforms the parameters to the provider-specific parameters.
const config: PromptSnapshotConfig = {
  providerName: 'openai',
  model: 'gpt-4o',
  settings: {
    temperature: 0.7,
    maxTokens: 1000, // 'max_tokens' in OpenAI, 'max_tokens' in Anthropic, 'maxOutputTokens' in Google, etc.
    topP: 0.9, // 'top_p' in OpenAI, 'top_p' in Anthropic, 'topP' in Google, etc.
    stopSequences: ['\n\n', 'END'] // 'stop' in OpenAI, 'stop' in Anthropic, 'stopSequences' in Google, etc.
  }
};

​
Using with Deployments

import { Adaline } from '@adaline/client';
import type { Deployment, PromptSnapshotConfig } from '@adaline/api';

const adaline = new Adaline();

const deployment: Deployment = await adaline.getLatestDeployment({
  promptId: 'prompt_123',
  deploymentEnvironmentId: 'environment_123'
});

// Access the prompt snapshot config
const config: PromptSnapshotConfig = deployment.prompt.config;

const temperature = config.settings?.temperature;
const maxTokens = config.settings?.maxTokens;

console.log(`Provider: ${config.providerName}`);
console.log(`Model: ${config.model}`);
console.log(`Temperature: ${temperature}`);
console.log(`Max Tokens: ${maxTokens}`);

// Use with Adaline Gateway (automatically transforms parameters per provider)
import { Gateway } from '@adaline/gateway';
import { OpenAI } from '@adaline/openai';

const gateway = new Gateway();
const openaiProvider = new OpenAI();

const model = openaiProvider.chatModel({
  modelName: config.model!,
  apiKey: process.env.OPENAI_API_KEY!
});

const gatewayResponse = await gateway.completeChat({
  model,
  config: config.settings,
  messages: deployment.prompt.messages,
  tools: deployment.prompt.tools
});

console.log(gatewayResponse.response.messages[0].content[0].value);