google-gemini-file-search

SKILL.md

Fully managed RAG with automatic chunking, embeddings, and citations for document Q&A.

Supports 100+ file formats (PDF, Word, Excel, code) with configurable chunking strategies optimized by content type (technical docs: 500 tokens/chunk, prose: 800, legal: 300)

Requires Gemini 3 Pro or Flash models; File Search and Google Search tools are mutually exclusive in single requests

Prevents 12 common errors including storage quota miscalculation (3x multiplier), document immutability (delete+re-upload pattern), polling timeouts with manual verification fallback, and metadata limits (20 max fields)

Pricing: $0.15 per 1M input tokens for one-time indexing; free tier includes 1 GB storage and 1,500 requests/day; includes cost estimation and deduplication strategies

Includes 3 working templates (basic Node.js, Cloudflare Workers edge deployment, Next.js full-stack) plus CLI tools for store creation, batch uploads, and interactive queries

Google Gemini File Search Setup

Overview

Google Gemini File Search is a fully managed RAG system. Upload documents (100+ formats: PDF, Word, Excel, code) and query with natural language—automatic chunking, embeddings, semantic search, and citations.

What This Skill Provides:

Complete @google/genai File Search API setup

8 documented errors with prevention strategies

Chunking best practices for optimal retrieval

Cost optimization ($0.15/1M tokens indexing, 3x storage multiplier)

Cloudflare Workers + Next.js integration templates

Prerequisites

1. Google AI API Key

Create an API key at https://aistudio.google.com/apikey