arize-experiment

Name: arize-experiment
Author: github

37kstars4.6kforks

How to install arize-experiment?

github/awesome-copilot/arize-experiment

$npx -y skills add github/awesome-copilot --skill arize-experiment

Installs into the current project.

Summary

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model

Files · 1

View on GitHub

SKILL.md

1	# Arize Experiment Skill
2
3	> `SPACE` — All `--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
5	## Concepts
6
7	- Experiment = a named evaluation run against a specific dataset version, containing one run per example
8	- Experiment Run = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata
9	- Dataset = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version
10	- Evaluation = a named metric attached to a run (e.g., `correctness`, `relevance`), with optional label, score, and explanation
11
12	The typical flow: export a dataset → process each example → collect outputs and evaluations → create an experiment with the runs.
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	- Project unclear → ask the user, or run `ax projects list -o json --limit 100` and present as selectable options
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	- CRITICAL — Never fabricate outputs: When running an experiment, you MUST call the real model API specified by the user for every dataset example. Never fabricate, simulate, or hardcode model outputs, latencies, or evaluation scores. If you cannot call the API (missing SDK, missing credentials, network error), stop and tell the user what is needed before proceeding.
25
26	## List Experiments: `ax experiments list`
27
28	Browse experiments, optionally filtered by dataset. Output goes to stdout.
29
30	```bash
31	ax experiments list
32	ax experiments list --dataset DATASET_NAME --space SPACE --limit 20 # DATASET_NAME: name or ID (name preferred)
33	ax experiments list --cursor CURSOR_TOKEN
34	ax experiments list -o json
35	```
36
37	### Flags
38
39	\| Flag \| Type \| Default \| Description \|
40	\|------\|------\|---------\|-------------\|
41	\| `--dataset` \| string \| none \| Filter by dataset \|
42	\| `--limit, -l` \| int \| 15 \| Max results (1-100) \|
43	\| `--cursor` \| string \| none \| Pagination cursor from previous response \|
44	\| `-o, --output` \| string \| table \| Output format: table, json, csv, parquet, or file path \|
45	\| `-p, --profile` \| string \| default \| Configuration profile \|
46
47	## Get Experiment: `ax experiments get`
48
49	Quick metadata lookup -- returns experiment name, linked dataset/version, and timestamps.
50
51	```bash
52	ax experiments get NAME_OR_ID
53	ax experiments get NAME_OR_ID -o json
54	ax experiments get NAME_OR_ID --dataset DATASET_NAME --space SPACE # required when using experiment name instead of ID
55	```
56
57	### Flags
58
59	\| Flag \| Type \| Default \| Description \|
60	\|------\|------\|---------\|-------------\|
61	\| `NAME_OR_ID` \| string \| required \| Experiment name or ID (positional) \|
62	\| `--dataset` \| string \| none \| Dataset name or ID (required if using experiment name instead of ID) \|
63	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
64	\| `-o, --output` \| string \| table \| Output format \|
65	\| `-p, --profile` \| string \| default \| Configuration profile \|
66
67	### Response fields
68
69	\| Field \| Type \| Description \|
70	\|-------\|------\|-------------\|
71	\| `id` \| string \| Experiment ID \|
72	\| `name` \| string \| Experiment name \|
73	\| `dataset_id` \| string \| Linked dataset ID \|
74	\| `dataset_version_id` \| string \| Specific dataset version used \|
75	\| `experiment_traces_project_id` \| string \| Project where experiment traces are stored \|
76	\| `created_at` \| datetime \| When the experiment was created \|
77	\| `updated_at` \| datetime \| Last modification time \|
78
79	## Export Experiment: `ax experiments export`
80
81	Download all runs to a file. By default uses the REST API; pass `--all` to use Arrow Flight for bulk transfer.
82
83	```bash
84	# EXPERIMENT_NAME, DATASET_

People who liked this also viewed

6 picks

Type

arize-experiment

37kstars4.6kforks

View on GitHub

How to install arize-experiment?

github/awesome-copilot/arize-experiment

$npx -y skills add github/awesome-copilot --skill arize-experiment

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Arize Experiment Skill
2
3	> `SPACE` — All `--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
5	## Concepts
6
7	- Experiment = a named evaluation run against a specific dataset version, containing one run per example
8	- Experiment Run = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata
9	- Dataset = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version
10	- Evaluation = a named metric attached to a run (e.g., `correctness`, `relevance`), with optional label, score, and explanation
11
12	The typical flow: export a dataset → process each example → collect outputs and evaluations → create an experiment with the runs.
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	- Project unclear → ask the user, or run `ax projects list -o json --limit 100` and present as selectable options
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	- CRITICAL — Never fabricate outputs: When running an experiment, you MUST call the real model API specified by the user for every dataset example. Never fabricate, simulate, or hardcode model outputs, latencies, or evaluation scores. If you cannot call the API (missing SDK, missing credentials, network error), stop and tell the user what is needed before proceeding.
25
26	## List Experiments: `ax experiments list`
27
28	Browse experiments, optionally filtered by dataset. Output goes to stdout.
29
30	```bash
31	ax experiments list
32	ax experiments list --dataset DATASET_NAME --space SPACE --limit 20 # DATASET_NAME: name or ID (name preferred)
33	ax experiments list --cursor CURSOR_TOKEN
34	ax experiments list -o json
35	```
36
37	### Flags
38
39	\| Flag \| Type \| Default \| Description \|
40	\|------\|------\|---------\|-------------\|
41	\| `--dataset` \| string \| none \| Filter by dataset \|
42	\| `--limit, -l` \| int \| 15 \| Max results (1-100) \|
43	\| `--cursor` \| string \| none \| Pagination cursor from previous response \|
44	\| `-o, --output` \| string \| table \| Output format: table, json, csv, parquet, or file path \|
45	\| `-p, --profile` \| string \| default \| Configuration profile \|
46
47	## Get Experiment: `ax experiments get`
48
49	Quick metadata lookup -- returns experiment name, linked dataset/version, and timestamps.
50
51	```bash
52	ax experiments get NAME_OR_ID
53	ax experiments get NAME_OR_ID -o json
54	ax experiments get NAME_OR_ID --dataset DATASET_NAME --space SPACE # required when using experiment name instead of ID
55	```
56
57	### Flags
58
59	\| Flag \| Type \| Default \| Description \|
60	\|------\|------\|---------\|-------------\|
61	\| `NAME_OR_ID` \| string \| required \| Experiment name or ID (positional) \|
62	\| `--dataset` \| string \| none \| Dataset name or ID (required if using experiment name instead of ID) \|
63	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
64	\| `-o, --output` \| string \| table \| Output format \|
65	\| `-p, --profile` \| string \| default \| Configuration profile \|
66
67	### Response fields
68
69	\| Field \| Type \| Description \|
70	\|-------\|------\|-------------\|
71	\| `id` \| string \| Experiment ID \|
72	\| `name` \| string \| Experiment name \|
73	\| `dataset_id` \| string \| Linked dataset ID \|
74	\| `dataset_version_id` \| string \| Specific dataset version used \|
75	\| `experiment_traces_project_id` \| string \| Project where experiment traces are stored \|
76	\| `created_at` \| datetime \| When the experiment was created \|
77	\| `updated_at` \| datetime \| Last modification time \|
78
79	## Export Experiment: `ax experiments export`
80
81	Download all runs to a file. By default uses the REST API; pass `--all` to use Arrow Flight for bulk transfer.
82
83	```bash
84	# EXPERIMENT_NAME, DATASET_

People who liked this also viewed

6 picks

Type