firebase-vertex-ai

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Firebase Vertex AI

Operate Firebase projects end-to-end (Auth, Firestore, Functions, Hosting) and integrate Gemini/Vertex AI safely for AI-powered features.

端到端操作Firebase项目（身份验证、Firestore、云函数、托管），并安全集成Gemini/Vertex AI以实现AI驱动功能。

Overview

概述

Use this skill to design, implement, and deploy Firebase applications that call Vertex AI/Gemini from Cloud Functions (or other GCP services) with secure secrets handling, least-privilege IAM, and production-ready observability.

使用此技能设计、实现并部署Firebase应用，这些应用可通过Cloud Functions（或其他GCP服务）调用Vertex AI/Gemini，同时具备安全的密钥管理、最小权限IAM配置以及生产级可观测性。

Prerequisites

前置条件

Node.js runtime and Firebase CLI access for the target project
A Firebase project (billing enabled for Functions/Vertex AI as needed)
Vertex AI API enabled and permissions to call Gemini/Vertex AI from your backend
Secrets managed via env vars or Secret Manager (never in client code)

目标项目需具备Node.js运行时环境及Firebase CLI访问权限
一个Firebase项目（根据需要为云函数/Vertex AI启用计费）
已启用Vertex AI API，且后端具备调用Gemini/Vertex AI的权限
通过环境变量或Secret Manager管理密钥（绝不要在客户端代码中存储）

Instructions

操作步骤

Initialize Firebase (or validate an existing repo): Hosting/Functions/Firestore as required.
Implement backend integration:
- add a Cloud Function/HTTP endpoint that calls Gemini/Vertex AI
- validate inputs and return structured responses
Configure data and security:
- Firestore rules + indexes
- Storage rules (if applicable)
- Auth providers and authorization checks
Deploy and verify:
- deploy Functions/Hosting
- run smoke tests against deployed endpoints
Add ops guardrails:
- logging/metrics
- alerting for error spikes
- basic cost controls (budgets/quotas) where appropriate

初始化Firebase（或验证现有仓库）：根据需要配置托管/云函数/Firestore。
实现后端集成：
- 添加一个调用Gemini/Vertex AI的Cloud Function/HTTP端点
- 验证输入并返回结构化响应
配置数据与安全：
- Firestore规则及索引
- 存储规则（如适用）
- 身份验证提供商及授权检查
部署与验证：
- 部署云函数/托管服务
- 针对已部署端点运行冒烟测试
添加运维防护措施：
- 日志/指标监控
- 错误峰值告警
- 酌情配置基础成本控制（预算/配额）

Output

输出结果

A deployable Firebase project structure (configs + Functions/Hosting as needed)
Secure backend code that calls Gemini/Vertex AI (with secrets handled correctly)
Firestore/Storage rules and index guidance
A verification checklist (local + deployed) and CI-ready commands

可部署的Firebase项目结构（含配置文件及所需的云函数/托管代码）
安全调用Gemini/Vertex AI的后端代码（密钥处理合规）
Firestore/存储规则及索引配置指南
本地及部署环境的验证清单，以及适用于CI的命令

Error Handling

错误处理

Auth failures: identify the principal and missing permission/role; fix with least privilege.
Billing/API issues: detect which API or quota is blocking and provide remediation steps.
Firestore rule/index problems: provide minimal repro queries and rule fixes.
Vertex AI call failures: surface model/region mismatches and add retries/backoff for transient errors.

身份验证失败：识别主体及缺失的权限/角色，通过最小权限原则修复。
计费/API问题：检测被阻塞的API或配额，并提供修复步骤。
Firestore规则/索引问题：提供最小化复现查询及规则修复方案。
Vertex AI调用失败：排查模型/区域不匹配问题，为瞬时错误添加重试/退避机制。

Examples

示例

Example: Gemini-backed chat API on Firebase

Request: “Deploy Hosting + a Function that powers a Gemini chat endpoint.”
Result:
```
/api/chat
```
function, Secret Manager wiring, and smoke tests.

Example: Firestore-powered RAG

Request: “Build a RAG flow that embeds docs and answers with citations.”
Result: ingestion plan, embedding + index strategy, and evaluation prompts.

示例：基于Gemini的Firebase聊天API

请求：“部署托管服务+一个支持Gemini聊天端点的云函数。”
结果：
```
/api/chat
```
云函数、Secret Manager配置及冒烟测试。

示例：基于Firestore的RAG系统

请求：“构建一个嵌入文档并带引用回答的RAG流程。”
结果：数据摄入方案、嵌入+索引策略及评估提示词。

Resources

参考资源

Full detailed guide (kept for reference):
```
{baseDir}/references/SKILL.full.md
```
Firebase docs: https://firebase.google.com/docs
Cloud Functions for Firebase: https://firebase.google.com/docs/functions
Vertex AI docs: https://cloud.google.com/vertex-ai/docs

详细完整指南（仅供参考）：
```
{baseDir}/references/SKILL.full.md
```
Firebase文档：https://firebase.google.com/docs
Firebase云函数文档：https://firebase.google.com/docs/functions
Vertex AI文档：https://cloud.google.com/vertex-ai/docs