$npx -y skills add github/awesome-copilot --skill arize-ai-provider-integrationCreates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI
| 1 | # Arize AI Integration Skill |
| 2 | |
| 3 | > **`SPACE`** — Most `--space` flags and the `ARIZE_SPACE` env var accept a space **name** (e.g., `my-workspace`) or a base64 space **ID** (e.g., `U3BhY2U6...`). Find yours with `ax spaces list`. |
| 4 | > **Note:** `ai-integrations create` does **not** accept `--space` — AI integrations are account-scoped. Use `--space` only with `list`, `get`, `update`, and `delete`. |
| 5 | |
| 6 | ## Concepts |
| 7 | |
| 8 | - **AI Integration** = stored LLM provider credentials registered in Arize; used by evaluators to call a judge model and by other Arize features that need to invoke an LLM on your behalf |
| 9 | - **Provider** = the LLM service backing the integration (e.g., `openAI`, `anthropic`, `awsBedrock`) |
| 10 | - **Integration ID** = a base64-encoded global identifier for an integration (e.g., `TGxtSW50ZWdyYXRpb246MTI6YUJjRA==`); required for evaluator creation and other downstream operations |
| 11 | - **Scoping** = visibility rules controlling which spaces or users can use an integration |
| 12 | - **Auth type** = how Arize authenticates with the provider: `default` (provider API key), `proxy_with_headers` (proxy via custom headers), or `bearer_token` (bearer token auth) |
| 13 | |
| 14 | ## Prerequisites |
| 15 | |
| 16 | Proceed directly with the task — run the `ax` command you need. Do NOT check versions, env vars, or profiles upfront. |
| 17 | |
| 18 | If an `ax` command fails, troubleshoot based on the error: |
| 19 | - `command not found` or version error → see references/ax-setup.md |
| 20 | - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong, follow references/ax-profiles.md to create/update it. If the user doesn't have their key, direct them to https://app.arize.com/admin > API Keys |
| 21 | - Space unknown → run `ax spaces list` to pick by name, or ask the user |
| 22 | - LLM provider call fails (missing OPENAI_API_KEY / ANTHROPIC_API_KEY) → run `ax ai-integrations list --space SPACE` to check for platform-managed credentials. If none exist, ask the user to provide the key or create an integration via the **arize-ai-provider-integration** skill |
| 23 | - **Security:** Never read `.env` files or search the filesystem for credentials. Use `ax profiles` for Arize credentials and `ax ai-integrations` for LLM provider keys. If credentials are not available through these channels, ask the user. |
| 24 | |
| 25 | --- |
| 26 | |
| 27 | ## List AI Integrations |
| 28 | |
| 29 | List all integrations accessible in a space: |
| 30 | |
| 31 | ```bash |
| 32 | ax ai-integrations list --space SPACE |
| 33 | ``` |
| 34 | |
| 35 | Filter by name (case-insensitive substring match): |
| 36 | |
| 37 | ```bash |
| 38 | ax ai-integrations list --space SPACE --name "openai" |
| 39 | ``` |
| 40 | |
| 41 | Paginate large result sets: |
| 42 | |
| 43 | ```bash |
| 44 | # Get first page |
| 45 | ax ai-integrations list --space SPACE --limit 20 -o json |
| 46 | |
| 47 | # Get next page using cursor from previous response |
| 48 | ax ai-integrations list --space SPACE --limit 20 --cursor CURSOR_TOKEN -o json |
| 49 | ``` |
| 50 | |
| 51 | **Key flags:** |
| 52 | |
| 53 | | Flag | Description | |
| 54 | |------|-------------| |
| 55 | | `--space` | Space name or ID to filter integrations | |
| 56 | | `--name` | Case-insensitive substring filter on integration name | |
| 57 | | `--limit` | Max results (1–100, default 15) | |
| 58 | | `--cursor` | Pagination token from a previous response | |
| 59 | | `-o, --output` | Output format: `table` (default) or `json` | |
| 60 | |
| 61 | **Response fields:** |
| 62 | |
| 63 | | Field | Description | |
| 64 | |-------|-------------| |
| 65 | | `id` | Base64 integration ID — copy this for downstream commands | |
| 66 | | `name` | Human-readable name | |
| 67 | | `provider` | LLM provider enum (see Supported Providers below) | |
| 68 | | `has_api_key` | `true` if credentials are stored | |
| 69 | | `model_names` | Allowed model list, or `null` if all models are enabled | |
| 70 | | `enable_default_models` | Whether default models for this provider are allowed | |
| 71 | | `function_calling_enabled` | Whether tool/function calling is enabled | |
| 72 | | `auth_type` | Authentication method: `default`, `proxy_with_headers`, or `bearer_token` | |
| 73 | |
| 74 | --- |
| 75 | |
| 76 | ## Get a Specific Integration |
| 77 | |
| 78 | ```bash |
| 79 | ax ai-integrations get NAME_OR_ID |
| 80 | ax ai-integrations get NAME_OR_ID -o json |
| 81 | ax ai-integrations get NAME_OR_ID --space SPACE # required when using name instead of ID |
| 82 | ``` |
| 83 | |
| 84 | Use this to inspect an integration's full configuration or to confirm its ID after creation. |
| 85 | |
| 86 | --- |
| 87 | |
| 88 | ## Create an AI Integration |
| 89 | |
| 90 | Before creating, always list integrations first — the user may already have a suitable one: |
| 91 | |
| 92 | ```bash |
| 93 | ax ai-integrations list --space SPACE |
| 94 | ``` |
| 95 | |
| 96 | If no suitable integration exists, create one. The required flags depend on the provider. |
| 97 | |
| 98 | ### OpenAI |
| 99 | |
| 100 | ```bash |
| 101 | ax ai-integrations create |