arize-ai-provider-integration

Manages Arize AI integrations storing LLM provider credentials via the ax CLI.

1|Updated Nov 9, 2025
One-click install
npx skills add https://github.com/akashjpal/question-generator --skill arize-ai-provider-integration-akashjpal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: arize-ai-provider-integration
Source: https://github.com/akashjpal/question-generator/tree/main/.agents/skills/arize-ai-provider-integration
Command: npx skills add https://github.com/akashjpal/question-generator --skill arize-ai-provider-integration-akashjpal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Configuring LLM provider credentials for Arize evaluators and other platform features requires knowing the correct provider enums, auth types, and CLI flags. This Skill manages the full lifecycle of Arize AI integrations so credentials are registered, updated, and removed correctly. ## Core Features & Use Cases - Integration CRUD: Create, list, get, update, and delete AI integrations through the ax ai-integrations command family. - Multi-provider support: Covers OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, and custom OpenAI-compatible endpoints with provider-specific flags. - Credential troubleshooting: Diagnoses 401 errors, missing profiles, and failed LLM calls using bundled ax CLI setup and profile references. - Use Case: Before creating an LLM-as-judge evaluator, use this Skill to register your OpenAI API key as an integration and capture its base64 integration ID for the evaluator configuration. ## Quick Start Ask the assistant to create an Arize AI integration for your OpenAI API key and return the integration ID for use in an evaluator.

Frequently Asked Questions about arize-ai-provider-integration

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

FAQPage Schema
How do I create an Arize AI integration for OpenAI?

Run ax ai-integrations create with --provider openAI, --api-key referencing your key, and a --name. First list existing integrations with ax ai-integrations list --space SPACE to avoid duplicates, then capture the returned base64 integration ID.

Which LLM providers does Arize AI integration support?

Supported providers include openAI, anthropic, azureOpenAI, awsBedrock, vertexAI, gemini, nvidiaNim, and custom OpenAI-compatible endpoints. Each provider has specific required flags such as --api-key, --base-url, or --provider-metadata.

How do I connect AWS Bedrock or Vertex AI to Arize?

AWS Bedrock uses IAM role-based auth via --provider-metadata with a role_arn, while Vertex AI uses --provider-metadata with project_id and location. Neither requires a direct API key flag.

Why does my Arize evaluator fail with LLM errors?

Evaluator LLM errors usually mean the backing integration has invalid or expired credentials. Inspect it with ax ai-integrations get INT_ID, check has_api_key, and rotate the key with ax ai-integrations update if needed.

Can I change the provider of an existing Arize integration?

No, the provider cannot be changed after creation. You must delete the existing integration with ax ai-integrations delete and recreate it with the correct provider value.

What should I do when ax commands return 401 Unauthorized?

A 401 means the API key lacks access to the space or is wrong. Run ax profiles show to inspect the current profile, then update the key via ax profiles update --api-key $ARIZE_API_KEY using a key from the Arize admin API Keys page.