Gemini API Integration

Gemini API Integration

Overview

This skill guides AI agents through integrating Google Gemini API into applications — from basic text generation to advanced multimodal, function calling, and streaming use cases. It covers the full Gemini SDK lifecycle with production-grade patterns.

When to Use This Skill

• Use when setting up Gemini API for the first time in a Node.js, Python, or browser project
• Use when implementing multimodal inputs (text + image/audio/video)
• Use when adding streaming responses to improve perceived latency
• Use when implementing function calling / tool use with Gemini
• Use when optimizing model selection (Flash vs Pro vs Ultra) for cost and performance
• Use when debugging Gemini API errors, rate limits, or quota issues

Step-by-Step Guide

1. Installation & Setup

Node.js / TypeScript:

npm install @google/generative-ai

Python:

pip install google-generativeai

Set your API key securely:

export GEMINI_API_KEY="your-api-key-here"

2. Basic Text Generation

Node.js:

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const result = await model.generateContent("Explain async/await in JavaScript");
console.log(result.response.text());

Python:

import google.generativeai as genai
import os

genai.configure(api_key=os.environ["GEMINI_API_KEY"])
model = genai.GenerativeModel("gemini-1.5-flash")

response = model.generate_content("Explain async/await in JavaScript")
print(response.text)

3. Streaming Responses

const result = await model.generateContentStream("Write a detailed blog post about AI");

for await (const chunk of result.stream) {
  process.stdout.write(chunk.text());
}

4. Multimodal Input (Text + Image)

import fs from "fs";

const imageData = fs.readFileSync("screenshot.png");
const imagePart = {
  inlineData: {
    data: imageData.toString("base64"),
    mimeType: "image/png",
  },
};

const result = await model.generateContent(["Describe this image:", imagePart]);
console.log(result.response.text());

5. Function Calling / Tool Use

const tools = [{
  functionDeclarations: [{
    name: "get_weather",
    description: "Get current weather for a city",
    parameters: {
      type: "OBJECT",
      properties: {
        city: { type: "STRING", description: "City name" },
      },
      required: ["city"],
    },
  }],
}];

const model = genAI.getGenerativeModel({ model: "gemini-1.5-pro", tools });
const result = await model.generateContent("What's the weather in Mumbai?");

const call = result.response.functionCalls()?.[0];
if (call) {
  // Execute the actual function
  const weatherData = await getWeather(call.args.city);
  // Send result back to model
}

6. Multi-turn Chat

const chat = model.startChat({
  history: [
    { role: "user", parts: [{ text: "You are a helpful coding assistant." }] },
    { role: "model", parts: [{ text: "Sure! I'm ready to help with code." }] },
  ],
});

const response = await chat.sendMessage("How do I reverse a string in Python?");
console.log(response.response.text());

7. Model Selection Guide

Best Practices

• ✅ Do: Use gemini-1.5-flash for most tasks — it's fast and cost-effective
• ✅ Do: Always stream responses for user-facing chat UIs to reduce perceived latency
• ✅ Do: Store API keys in environment variables, never hard-code them
• ✅ Do: Implement exponential backoff for rate limit (429) errors
• ✅ Do: Use systemInstruction to set persistent model behavior
• ❌ Don't: Use gemini-pro for simple tasks — Flash is cheaper and faster
• ❌ Don't: Send large base64 images inline for files > 20MB — use File API instead
• ❌ Don't: Ignore safety ratings in responses for production apps

Error Handling

try {
  const result = await model.generateContent(prompt);
  return result.response.text();
} catch (error) {
  if (error.status === 429) {
    // Rate limited — wait and retry with exponential backoff
    await new Promise(r => setTimeout(r, 2 ** retryCount * 1000));
  } else if (error.status === 400) {
    // Invalid request — check prompt or parameters
    console.error("Invalid request:", error.message);
  } else {
    throw error;
  }
}

Troubleshooting

Problem: API_KEY_INVALID error Solution: Ensure GEMINI_API_KEY environment variable is set and the key is active in Google AI Studio.

Problem: Response blocked by safety filters Solution: Check result.response.promptFeedback.blockReason and adjust your prompt or safety settings.

Problem: Slow response times Solution: Switch to gemini-1.5-flash and enable streaming. Consider caching repeated prompts.

Problem: RESOURCE_EXHAUSTED (quota exceeded) Solution: Check your quota in Google Cloud Console. Implement request queuing and exponential backoff.

AGI Framework Integration

Adapted for @techwavedev/agi-agent-kit Original source: antigravity-awesome-skills

Memory-First Protocol

Retrieve prior API design decisions, database schema choices, and error handling patterns. Cache API response templates for consistent error formatting.

# Check for prior backend/API context before starting
python3 execution/memory_manager.py auto --query "API design patterns and architecture decisions for Gemini Api Integration"

Storing Results

After completing work, store backend/API decisions for future sessions:

python3 execution/memory_manager.py store \
  --content "API architecture: REST with HATEOAS, JWT auth, rate limiting at 100 req/min per tenant" \
  --type decision --project <project> \
  --tags gemini-api-integration backend

Multi-Agent Collaboration

Share API contract changes with frontend agents so they update their client code, and with QA agents for test coverage.

python3 execution/cross_agent_context.py store \
  --agent "<your-agent>" \
  --action "Implemented API endpoints — 5 new routes with OpenAPI spec and integration tests" \
  --project <project>

Agent Team: Code Review

After implementation, dispatch code_review_team for two-stage review (spec compliance + code quality) before merging.