🤖

OpenAI Integration

Popular
AI & Machine Learning

Use SERPII data with GPT function calling for real-time search augmented generation (RAG)

Official Documentation

Features

Function Calling

Use SERPII as a tool in GPT function calling for real-time web search capabilities.

RAG Pipelines

Build retrieval augmented generation systems with fresh SERP data.

Real-time Data

Provide GPT with up-to-date information from search engines.

Context Enhancement

Enhance AI responses with relevant search results and knowledge.

Setup

Step 1

Install Dependencies

Install the OpenAI SDK and axios for API calls.

npm install openai axios
Step 2

Configure API Keys

Set up your OpenAI and SERPII API keys in environment variables.

# .env
OPENAI_API_KEY=sk-...
SERPII_API_KEY=your_serpii_api_key
Step 3

Create SERPII Function

Define a function that GPT can call to search the web.

const searchTool = {
  type: "function",
  function: {
    name: "search_web",
    description: "Search the web for current information",
    parameters: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description: "The search query"
        },
        engine: {
          type: "string",
          enum: ["google", "bing", "yahoo"],
          description: "Search engine to use"
        }
      },
      required: ["query"]
    }
  }
};

Code Examples

import OpenAI from "openai";
import axios from "axios";

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY
});

async function searchWeb(query, engine = "google") {
  const response = await axios.get(
    `https://api.serpii.com/v1/${engine}/light/search`,
    {
      params: { q: query },
      headers: {
        "x-api-key": process.env.SERPII_API_KEY
      }
    }
  );
  return response.data.organic_results;
}

async function chat(userMessage) {
  const messages = [
    {
      role: "user",
      content: userMessage
    }
  ];

  // First API call - GPT decides if it needs to search
  let response = await openai.chat.completions.create({
    model: "gpt-4-turbo-preview",
    messages,
    tools: [searchTool],
    tool_choice: "auto"
  });

  // If GPT wants to search
  if (response.choices[0].message.tool_calls) {
    const toolCall = response.choices[0].message.tool_calls[0];
    const args = JSON.parse(toolCall.function.arguments);

    // Call SERPII
    const searchResults = await searchWeb(args.query, args.engine);

    // Add search results to conversation
    messages.push(response.choices[0].message);
    messages.push({
      role: "tool",
      tool_call_id: toolCall.id,
      content: JSON.stringify(searchResults.slice(0, 5))
    });

    // Get final response with search context
    response = await openai.chat.completions.create({
      model: "gpt-4-turbo-preview",
      messages
    });
  }

  return response.choices[0].message.content;
}

// Example usage
const answer = await chat("What are the latest trends in AI for 2024?");
console.log(answer);

Common Use Cases

  • →Real-time web search for AI chatbots
  • →Fact-checking and verification
  • →Research assistance with current data
  • →Content generation with up-to-date information
  • →Competitive intelligence gathering
  • →News aggregation and summarization