Skip to content

Commit 4d2b7f2

Browse files
github-actions[bot]github-actions[bot]
committed
chore: publish from staged
1 parent d791831 commit 4d2b7f2

File tree

407 files changed

+85783
-237
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

407 files changed

+85783
-237
lines changed

‎docs/README.plugins.md‎

Lines changed: 13 additions & 13 deletions
Large diffs are not rendered by default.

‎plugins/arize-ax/.github/plugin/plugin.json‎

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -19,14 +19,14 @@
1919
"prompt-optimization"
2020
],
2121
"skills": [
22-
"./skills/arize-ai-provider-integration/",
23-
"./skills/arize-annotation/",
24-
"./skills/arize-dataset/",
25-
"./skills/arize-evaluator/",
26-
"./skills/arize-experiment/",
27-
"./skills/arize-instrumentation/",
28-
"./skills/arize-link/",
29-
"./skills/arize-prompt-optimization/",
30-
"./skills/arize-trace/"
22+
"./skills/arize-ai-provider-integration",
23+
"./skills/arize-annotation",
24+
"./skills/arize-dataset",
25+
"./skills/arize-evaluator",
26+
"./skills/arize-experiment",
27+
"./skills/arize-instrumentation",
28+
"./skills/arize-link",
29+
"./skills/arize-prompt-optimization",
30+
"./skills/arize-trace"
3131
]
3232
}

‎plugins/arize-ax/skills/arize-ai-provider-integration/SKILL.md‎

Lines changed: 268 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,268 @@
1+
---
2+
name: arize-ai-provider-integration
3+
description: "INVOKE THIS SKILL when creating, reading, updating, or deleting Arize AI integrations. Covers listing integrations, creating integrations for any supported LLM provider (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, custom), updating credentials or metadata, and deleting integrations using the ax CLI."
4+
---
5+
6+
# Arize AI Integration Skill
7+
8+
## Concepts
9+
10+
- **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
11+
- **Provider** = the LLM service backing the integration (e.g., `openAI`, `anthropic`, `awsBedrock`)
12+
- **Integration ID** = a base64-encoded global identifier for an integration (e.g., `TGxtSW50ZWdyYXRpb246MTI6YUJjRA==`); required for evaluator creation and other downstream operations
13+
- **Scoping** = visibility rules controlling which spaces or users can use an integration
14+
- **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)
15+
16+
## Prerequisites
17+
18+
Proceed directly with the task — run the `ax` command you need. Do NOT check versions, env vars, or profiles upfront.
19+
20+
If an `ax` command fails, troubleshoot based on the error:
21+
- `command not found` or version error → see references/ax-setup.md
22+
- `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: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via references/ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys)
23+
- Space ID unknown → check `.env` for `ARIZE_SPACE_ID`, or run `ax spaces list -o json`, or ask the user
24+
- LLM provider call fails (missing OPENAI_API_KEY / ANTHROPIC_API_KEY) → check `.env`, load if present, otherwise ask the user
25+
26+
---
27+
28+
## List AI Integrations
29+
30+
List all integrations accessible in a space:
31+
32+
```bash
33+
ax ai-integrations list --space-id SPACE_ID
34+
```
35+
36+
Filter by name (case-insensitive substring match):
37+
38+
```bash
39+
ax ai-integrations list --space-id SPACE_ID --name "openai"
40+
```
41+
42+
Paginate large result sets:
43+
44+
```bash
45+
# Get first page
46+
ax ai-integrations list --space-id SPACE_ID --limit 20 -o json
47+
48+
# Get next page using cursor from previous response
49+
ax ai-integrations list --space-id SPACE_ID --limit 20 --cursor CURSOR_TOKEN -o json
50+
```
51+
52+
**Key flags:**
53+
54+
| Flag | Description |
55+
|------|-------------|
56+
| `--space-id` | Space to list integrations in |
57+
| `--name` | Case-insensitive substring filter on integration name |
58+
| `--limit` | Max results (1–100, default 50) |
59+
| `--cursor` | Pagination token from a previous response |
60+
| `-o, --output` | Output format: `table` (default) or `json` |
61+
62+
**Response fields:**
63+
64+
| Field | Description |
65+
|-------|-------------|
66+
| `id` | Base64 integration ID — copy this for downstream commands |
67+
| `name` | Human-readable name |
68+
| `provider` | LLM provider enum (see Supported Providers below) |
69+
| `has_api_key` | `true` if credentials are stored |
70+
| `model_names` | Allowed model list, or `null` if all models are enabled |
71+
| `enable_default_models` | Whether default models for this provider are allowed |
72+
| `function_calling_enabled` | Whether tool/function calling is enabled |
73+
| `auth_type` | Authentication method: `default`, `proxy_with_headers`, or `bearer_token` |
74+
75+
---
76+
77+
## Get a Specific Integration
78+
79+
```bash
80+
ax ai-integrations get INT_ID
81+
ax ai-integrations get INT_ID -o json
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-id SPACE_ID
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 \
102+
--name "My OpenAI Integration" \
103+
--provider openAI \
104+
--api-key $OPENAI_API_KEY
105+
```
106+
107+
### Anthropic
108+
109+
```bash
110+
ax ai-integrations create \
111+
--name "My Anthropic Integration" \
112+
--provider anthropic \
113+
--api-key $ANTHROPIC_API_KEY
114+
```
115+
116+
### Azure OpenAI
117+
118+
```bash
119+
ax ai-integrations create \
120+
--name "My Azure OpenAI Integration" \
121+
--provider azureOpenAI \
122+
--api-key $AZURE_OPENAI_API_KEY \
123+
--base-url "https://my-resource.openai.azure.com/"
124+
```
125+
126+
### AWS Bedrock
127+
128+
AWS Bedrock uses IAM role-based auth instead of an API key. Provide the ARN of the role Arize should assume:
129+
130+
```bash
131+
ax ai-integrations create \
132+
--name "My Bedrock Integration" \
133+
--provider awsBedrock \
134+
--role-arn "arn:aws:iam::123456789012:role/ArizeBedrockRole"
135+
```
136+
137+
### Vertex AI
138+
139+
Vertex AI uses GCP service account credentials. Provide the GCP project and region:
140+
141+
```bash
142+
ax ai-integrations create \
143+
--name "My Vertex AI Integration" \
144+
--provider vertexAI \
145+
--project-id "my-gcp-project" \
146+
--location "us-central1"
147+
```
148+
149+
### Gemini
150+
151+
```bash
152+
ax ai-integrations create \
153+
--name "My Gemini Integration" \
154+
--provider gemini \
155+
--api-key $GEMINI_API_KEY
156+
```
157+
158+
### NVIDIA NIM
159+
160+
```bash
161+
ax ai-integrations create \
162+
--name "My NVIDIA NIM Integration" \
163+
--provider nvidiaNim \
164+
--api-key $NVIDIA_API_KEY \
165+
--base-url "https://integrate.api.nvidia.com/v1"
166+
```
167+
168+
### Custom (OpenAI-compatible endpoint)
169+
170+
```bash
171+
ax ai-integrations create \
172+
--name "My Custom Integration" \
173+
--provider custom \
174+
--base-url "https://my-llm-proxy.example.com/v1" \
175+
--api-key $CUSTOM_LLM_API_KEY
176+
```
177+
178+
### Supported Providers
179+
180+
| Provider | Required extra flags |
181+
|----------|---------------------|
182+
| `openAI` | `--api-key <key>` |
183+
| `anthropic` | `--api-key <key>` |
184+
| `azureOpenAI` | `--api-key <key>`, `--base-url <azure-endpoint>` |
185+
| `awsBedrock` | `--role-arn <arn>` |
186+
| `vertexAI` | `--project-id <gcp-project>`, `--location <region>` |
187+
| `gemini` | `--api-key <key>` |
188+
| `nvidiaNim` | `--api-key <key>`, `--base-url <nim-endpoint>` |
189+
| `custom` | `--base-url <endpoint>` |
190+
191+
### Optional flags for any provider
192+
193+
| Flag | Description |
194+
|------|-------------|
195+
| `--model-names` | Comma-separated list of allowed model names; omit to allow all models |
196+
| `--enable-default-models` / `--no-default-models` | Enable or disable the provider's default model list |
197+
| `--function-calling` / `--no-function-calling` | Enable or disable tool/function calling support |
198+
199+
### After creation
200+
201+
Capture the returned integration ID (e.g., `TGxtSW50ZWdyYXRpb246MTI6YUJjRA==`) — it is needed for evaluator creation and other downstream commands. If you missed it, retrieve it:
202+
203+
```bash
204+
ax ai-integrations list --space-id SPACE_ID -o json
205+
# or, if you know the ID:
206+
ax ai-integrations get INT_ID
207+
```
208+
209+
---
210+
211+
## Update an AI Integration
212+
213+
`update` is a partial update — only the flags you provide are changed. Omitted fields stay as-is.
214+
215+
```bash
216+
# Rename
217+
ax ai-integrations update INT_ID --name "New Name"
218+
219+
# Rotate the API key
220+
ax ai-integrations update INT_ID --api-key $OPENAI_API_KEY
221+
222+
# Change the model list
223+
ax ai-integrations update INT_ID --model-names "gpt-4o,gpt-4o-mini"
224+
225+
# Update base URL (for Azure, custom, or NIM)
226+
ax ai-integrations update INT_ID --base-url "https://new-endpoint.example.com/v1"
227+
```
228+
229+
Any flag accepted by `create` can be passed to `update`.
230+
231+
---
232+
233+
## Delete an AI Integration
234+
235+
**Warning:** Deletion is permanent. Evaluators that reference this integration will no longer be able to run.
236+
237+
```bash
238+
ax ai-integrations delete INT_ID --force
239+
```
240+
241+
Omit `--force` to get a confirmation prompt instead of deleting immediately.
242+
243+
---
244+
245+
## Troubleshooting
246+
247+
| Problem | Solution |
248+
|---------|----------|
249+
| `ax: command not found` | See references/ax-setup.md |
250+
| `401 Unauthorized` | API key may not have access to this space. Verify key and space ID at https://app.arize.com/admin > API Keys |
251+
| `No profile found` | Run `ax profiles show --expand`; set `ARIZE_API_KEY` env var or write `~/.arize/config.toml` |
252+
| `Integration not found` | Verify with `ax ai-integrations list --space-id SPACE_ID` |
253+
| `has_api_key: false` after create | Credentials were not saved — re-run `update` with the correct `--api-key` or `--role-arn` |
254+
| Evaluator runs fail with LLM errors | Check integration credentials with `ax ai-integrations get INT_ID`; rotate the API key if needed |
255+
| `provider` mismatch | Cannot change provider after creation — delete and recreate with the correct provider |
256+
257+
---
258+
259+
## Related Skills
260+
261+
- **arize-evaluator**: Create LLM-as-judge evaluators that use an AI integration → use `arize-evaluator`
262+
- **arize-experiment**: Run experiments that use evaluators backed by an AI integration → use `arize-experiment`
263+
264+
---
265+
266+
## Save Credentials for Future Use
267+
268+
See references/ax-profiles.md § Save Credentials for Future Use.

0 commit comments

Comments
 (0)