skills.rest
wangx7
wangx7COMMUNITY
Explore all skills by this author →
GitHub

agent-platform-inference

Generate code for calling Google Cloud Agent Platform GenAI models across SDKs.

Updated Jun 26, 2026
Search Tags:#troubleshooting#gemini#google cloud#sdk integration#agent platform#openmaas#genai inference
One-click install
npx skills add https://github.com/wangx7/skills-collection --skill agent-platform-inference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-platform-inference
Source: https://github.com/wangx7/skills-collection/tree/main/google-skills/skills/cloud/agent-platform-inference
Command: npx skills add https://github.com/wangx7/skills-collection --skill agent-platform-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, google-cloud-aiplatform, openai, google-auth, and includes scripts (resource) components.

What problem does it solve?

This Skill eliminates the hassle of manually configuring connections to Google Cloud Agent Platform GenAI models, handling authentication across multiple SDKs, setting up correct endpoints, and diagnosing common inference errors like 429 Resource Exhausted, 400 User Validation, and 404 Not Found, which typically require sifting through scattered documentation.

Core Features & Use Cases

  • Multi-Model Inference Support: Generate code for calling both first-party Gemini models and third-party OpenMaaS models (Llama, DeepSeek, Qwen, etc.) on Google Cloud Agent Platform.
  • Cross-SDK Compatibility: Provides guidance and example code for using the GenAI SDK, OpenAI SDK, and legacy Vertex AI SDK for model calls.
  • Error Troubleshooting: Includes step-by-step fixes for common inference errors, including DSQ quota management for 429 errors and region validation for 404 errors.
  • Use Case: A developer needs to call a DeepSeek model via the OpenAI SDK for a production workload, encounters a 429 Resource Exhausted error, and uses this Skill to implement exponential backoff and verify the correct global endpoint configuration.

Quick Start

Use the agent-platform-inference skill to generate Python code for calling the gemini-2.5-pro model via the GenAI SDK with proper Google Cloud authentication and endpoint setup.

Frequently Asked Questions about agent-platform-inference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run inference for third-party models like DeepSeek and Llama on Google Cloud Agent Platform?▼

To run inference for third-party models on Google Cloud Agent Platform, you can use the OpenMaaS integration. This Skill provides code generation for calling Llama, DeepSeek, and Qwen models via the GenAI SDK, OpenAI SDK, or Vertex AI SDK.

Why does my GenAI inference call return a 429 Resource Exhausted error on Google Cloud?▼

A 429 Resource Exhausted error during GenAI inference indicates quota limits. You can resolve this by verifying your DSQ quota management and implementing exponential backoff in your SDK calls as guided by this Skill.

Can I use the OpenAI SDK to call Gemini models on the Google Cloud Agent Platform?▼

Yes, you can use the OpenAI SDK to call Gemini models. This Skill supports cross-SDK compatibility, providing endpoint configuration and example code for using OpenAI SDK alongside GenAI and legacy Vertex AI SDKs.

How do I fix a 404 Not Found error when calling a GenAI model in Vertex AI?▼

A 404 Not Found error during GenAI inference usually means an incorrect model ID or region. This Skill helps troubleshoot by validating your model ID and verifying the correct global endpoint configuration for your workload.

What Google Cloud authentication setup is required for Agent Platform GenAI inference?▼

Google Cloud Agent Platform GenAI inference requires proper authentication setup using google-auth. This Skill ensures your environment is configured correctly to authorize requests across first-party Gemini and third-party OpenMaaS models.

How do I resolve a 400 User Validation error when calling Gemini models via the GenAI SDK?▼

A 400 User Validation error during GenAI SDK calls indicates incorrect request parameters or endpoint setup. This Skill provides step-by-step troubleshooting to validate your configurations and resolve SDK integration errors.

Related Skills

Explore More Software Engineering Skills→
pxlcrtivpxlcrtiv

gemini-api

Integrate the Gemini API using Google Gen AI SDKs for Python, JS/TS, Go, Java, and C#.

Community
Advanced
synaptiaisynaptiai
4

receive

Parse API, webhook, file, and sensor data into validated structured payloads.

Official
Intermediate
2nth-ai2nth-ai
1

tech/google/cloud/ai

Deploy and manage AI/ML models on Google Cloud Vertex AI endpoints.

Official
Advanced
zainhaszainhas
2

together-dedicated-containers

Deploy Dockerized inference workloads on Together AI's managed GPU infrastructure.

Community
Advanced