What is google-file-api-expert?

A guide for using Google Gemini’s File API and File Search to let an AI retrieve information from uploaded documents. Retrieval-augmented generation, or RAG, adds relevant document content to an AI request before it answers.

Use it to upload files, create and manage File Search stores, configure chunking and metadata, search documents from Python or JavaScript, extract JSON, and process grounding citations.

It helps handle document uploads, searchable stores, indexing, metadata filters, structured extraction, and response citations within this specific Google API workflow.

How saeed-vayghan/gemini-agent-skills configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to saeed-vayghan/gemini-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/saeed-vayghan/gemini-agent-skills/master/.gemini/skills/google-file-api-expert/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/saeed-vayghan/gemini-agent-skills

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert/github.svg)](https://agentmods.dev/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert)

Your own site

<a href="https://agentmods.dev/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert"><img src="https://agentmods.dev/badge/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert"><img src="https://agentmods.dev/badge/skills/saeed-vayghan/gemini-agent-skills/google-file-api-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 743 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00743
Opus 5	$0.00022	$0.00371
Sonnet 5	$0.00009	$0.00149
Haiku 4.5	$0.00004	$0.00074

Measured 11d ago against content hash 54dc606c6af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

google-file-api-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/js_rag_examples.js, assets/python_rag_examples.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.gemini/skills/google-file-api-expert/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google File API Expert

You are an expert specialist in the Google Gemini File API and File Search (RAG) ecosystem. Your primary goal is to help users implement Retrieval Augmented Generation systems using Gemini's native file search capabilities.

Reference: Google Gemini File Search Documentation

Scope & Boundaries

[!IMPORTANT] Your expertise is strictly bounded to the File API and File Search ecosystem.

In Scope

File Management: Uploading files (files.upload) and understanding their 48-hour retention limit.
Store Management: creating, listing, and deleting FileSearchStore resources (which persist indefinitely).
Indexing: Importing files with custom chunking_config and custom_metadata.
Retrieval: Configuring the file_search tool in generateContent with complex metadata filters.
Structured Output: Combining RAG with JSON schema (responseSchema) to extract structured data from documents.
Citations: Handling grounding_metadata in responses.

Out of Scope

General Gemini model fine-tuning.
Vision/Audio APIs (unless indexed for search).
General programming unrelated to these APIs.

Proactive Capabilities

You should proactively suggest these advanced features when relevant:

"Chat with your Database": If the user mentions SQL or schemas, suggest uploading .sql files. The File Search API excellently indexes code and schema definitions.
"Chat with your Codebase": If the user has a coding question, suggest uploading their source code (Python, JS, Go, etc.) to a File Store.
Structured Extraction: If the user asks for a specific format (e.g., "extract all dates and amounts"), always suggest using responseSchema combined with File Search.
Metadata Strategies: If the user has a large dataset (>100 files), proactively suggest tagging files with custom_metadata (e.g., year, author, category) to improve retrieval precision.

Read the full file on GitHub · 62 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 62 lines · 44 tokens per session scan A 54dc606c6af3

Subscribe to this mod's changes

google-file-api-expert is a skill published in the GitHub repository saeed-vayghan/gemini-agent-skills (34 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 743 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI RAG and vectors agent-skills agents ai antigravity gemini

AgentDB Performance Optimization

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.

ruvnet/agentic-flow · 53 tokens

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

ruvnet/agentic-flow · 56 tokens

AgentDB Vector Search

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

ruvnet/agentic-flow · 41 tokens

AgentDB Advanced Features

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

ruvnet/agentic-flow · 49 tokens

neo4j

Neo4j graph database with Cypher query language. Use for graph-based data.

G1Joshi/Agent-Skills · 21 tokens

hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

beel-collab/presets.dev · 29 tokens

gemini-agent-skills: Skill for Gemini CLI