OpenAI

Overview

OpenAI serves as the primary LLM provider in Lillo, implemented through the OpenAI Node.js SDK with support for GPT models and function calling.

Implementation

Provider Setup

import OpenAI from 'openai';

class OpenAIProvider implements LLMProvider {
  private client: OpenAI;

  constructor() {
    this.client = new OpenAI({
      apiKey: process.env.OPENAI_API_KEY,
    });
  }
}

Message Generation

async generateResponse(
  messages: Array<{ role: string; content: string }>
): Promise<LLMResponse> {
  const formattedMessages = messages.map(msg => ({
    role: msg.role as 'user' | 'assistant' | 'system',
    content: msg.content
  }));

  // Implementation details
}

Function Calling

Available Functions

const functions = {
  generate_image: {
    name: "generate_image",
    description: "Generate an image based on the prompt",
    parameters: {
      type: "object",
      properties: {
        prompt: {
          type: "string",
          description: "The description of the image to generate"
        }
      },
      required: ["prompt"]
    }
  },
  get_weather: {
    name: "get_weather",
    description: "Get current weather data",
    parameters: {
      type: "object",
      properties: {
        location: {
          type: "object",
          description: "Location details",
          properties: {
            name: { type: "string" },
            country: { type: "string" },
            coordinates: {
              type: "object",
              properties: {
                lat: { type: "number" },
                lon: { type: "number" }
              }
            }
          }
        }
      }
    }
  }
}

Error Handling

Common Errors

• Rate limiting

• Content policy violations

• Token limits

• Invalid requests

Error Response Format

interface ErrorResponse {
  error: true;
  content: string;
  type?: string;
  retryAfter?: number;
}

Best Practices

Configuration

• Use environment variables for API keys

• Configure request timeouts

• Set appropriate temperature

• Manage token limits

Message Handling

• Validate message roles

• Clean input content

• Format system prompts

• Handle streaming properly

Security

• Secure API key storage

• Input validation

• Response sanitization

• Error masking

Related Documentation

• LLM Factory

• Function Calling

• API Reference