arize-dataset

Name: arize-dataset
Author: github

37kstars4.6kforks

How to install arize-dataset?

github/awesome-copilot/arize-dataset

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

Installs into the current project.

Summary

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset,

Files · 1

View on GitHub

SKILL.md

1	# Arize Dataset 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	- Dataset = a versioned collection of examples used for evaluation and experimentation
8	- Dataset Version = a snapshot of a dataset at a point in time; updates can be in-place or create a new version
9	- Example = a single record in a dataset with arbitrary user-defined fields (e.g., `question`, `answer`, `context`)
10	- Space = an organizational container; datasets belong to a space
11
12	System-managed fields on examples (`id`, `created_at`, `updated_at`) are auto-generated by the server -- never include them in create or append payloads.
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
25	## List Datasets: `ax datasets list`
26
27	Browse datasets in a space. Output goes to stdout.
28
29	```bash
30	ax datasets list
31	ax datasets list --space SPACE --limit 20
32	ax datasets list --cursor CURSOR_TOKEN
33	ax datasets list -o json
34	```
35
36	### Flags
37
38	\| Flag \| Type \| Default \| Description \|
39	\|------\|------\|---------\|-------------\|
40	\| `--space` \| string \| from profile \| Filter by space \|
41	\| `--limit, -l` \| int \| 15 \| Max results (1-100) \|
42	\| `--cursor` \| string \| none \| Pagination cursor from previous response \|
43	\| `-o, --output` \| string \| table \| Output format: table, json, csv, parquet, or file path \|
44	\| `-p, --profile` \| string \| default \| Configuration profile \|
45
46	## Get Dataset: `ax datasets get`
47
48	Quick metadata lookup -- returns dataset name, space, timestamps, and version list.
49
50	```bash
51	ax datasets get NAME_OR_ID
52	ax datasets get NAME_OR_ID -o json
53	ax datasets get NAME_OR_ID --space SPACE # required when using dataset name instead of ID
54	```
55
56	### Flags
57
58	\| Flag \| Type \| Default \| Description \|
59	\|------\|------\|---------\|-------------\|
60	\| `NAME_OR_ID` \| string \| required \| Dataset name or ID (positional) \|
61	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
62	\| `-o, --output` \| string \| table \| Output format \|
63	\| `-p, --profile` \| string \| default \| Configuration profile \|
64
65	### Response fields
66
67	\| Field \| Type \| Description \|
68	\|-------\|------\|-------------\|
69	\| `id` \| string \| Dataset ID \|
70	\| `name` \| string \| Dataset name \|
71	\| `space_id` \| string \| Space this dataset belongs to \|
72	\| `created_at` \| datetime \| When the dataset was created \|
73	\| `updated_at` \| datetime \| Last modification time \|
74	\| `versions` \| array \| List of dataset versions (id, name, dataset_id, created_at, updated_at) \|
75
76	## Export Dataset: `ax datasets export`
77
78	Download all examples to a file. Use `--all` for datasets larger than 500 examples (unlimited bulk export).
79
80	```bash
81	ax datasets export NAME_OR_ID
82	# -> dataset_abc123_20260305_141500/examples.json
83
84	ax datasets export NAME_OR_ID --all
85	ax datasets export NAME_OR_ID --version-id VERSION_ID
86	ax datasets export NAME_OR_ID --output-dir ./data
87	ax datasets export NAME_OR_ID --stdout
88	ax datasets export NAME_OR_ID --stdout \| jq '.[0]'
89	ax datasets export NAME_OR_ID --space SPACE # required when using dataset name instead of ID
90	```
91
92	### Flags
93
94	\| Flag \| Type \| Default \| Description \|
95	\|------\|------\|---------\|-------------\|
96	\| `NAME_OR_ID` \| string \| required \| Dataset name or ID (positional) \|
97	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
98	\| `--version-id` \| string \| latest \| Export a specific dataset version \|
99	\| `--all` \| bool \| false \| Unlimited bulk export (use for datasets > 500 examples) \|
100	\| `--output-dir` \| s

People who liked this also viewed

6 picks

Type

arize-dataset

37kstars4.6kforks

View on GitHub

How to install arize-dataset?

github/awesome-copilot/arize-dataset

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Arize Dataset 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	- Dataset = a versioned collection of examples used for evaluation and experimentation
8	- Dataset Version = a snapshot of a dataset at a point in time; updates can be in-place or create a new version
9	- Example = a single record in a dataset with arbitrary user-defined fields (e.g., `question`, `answer`, `context`)
10	- Space = an organizational container; datasets belong to a space
11
12	System-managed fields on examples (`id`, `created_at`, `updated_at`) are auto-generated by the server -- never include them in create or append payloads.
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
25	## List Datasets: `ax datasets list`
26
27	Browse datasets in a space. Output goes to stdout.
28
29	```bash
30	ax datasets list
31	ax datasets list --space SPACE --limit 20
32	ax datasets list --cursor CURSOR_TOKEN
33	ax datasets list -o json
34	```
35
36	### Flags
37
38	\| Flag \| Type \| Default \| Description \|
39	\|------\|------\|---------\|-------------\|
40	\| `--space` \| string \| from profile \| Filter by space \|
41	\| `--limit, -l` \| int \| 15 \| Max results (1-100) \|
42	\| `--cursor` \| string \| none \| Pagination cursor from previous response \|
43	\| `-o, --output` \| string \| table \| Output format: table, json, csv, parquet, or file path \|
44	\| `-p, --profile` \| string \| default \| Configuration profile \|
45
46	## Get Dataset: `ax datasets get`
47
48	Quick metadata lookup -- returns dataset name, space, timestamps, and version list.
49
50	```bash
51	ax datasets get NAME_OR_ID
52	ax datasets get NAME_OR_ID -o json
53	ax datasets get NAME_OR_ID --space SPACE # required when using dataset name instead of ID
54	```
55
56	### Flags
57
58	\| Flag \| Type \| Default \| Description \|
59	\|------\|------\|---------\|-------------\|
60	\| `NAME_OR_ID` \| string \| required \| Dataset name or ID (positional) \|
61	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
62	\| `-o, --output` \| string \| table \| Output format \|
63	\| `-p, --profile` \| string \| default \| Configuration profile \|
64
65	### Response fields
66
67	\| Field \| Type \| Description \|
68	\|-------\|------\|-------------\|
69	\| `id` \| string \| Dataset ID \|
70	\| `name` \| string \| Dataset name \|
71	\| `space_id` \| string \| Space this dataset belongs to \|
72	\| `created_at` \| datetime \| When the dataset was created \|
73	\| `updated_at` \| datetime \| Last modification time \|
74	\| `versions` \| array \| List of dataset versions (id, name, dataset_id, created_at, updated_at) \|
75
76	## Export Dataset: `ax datasets export`
77
78	Download all examples to a file. Use `--all` for datasets larger than 500 examples (unlimited bulk export).
79
80	```bash
81	ax datasets export NAME_OR_ID
82	# -> dataset_abc123_20260305_141500/examples.json
83
84	ax datasets export NAME_OR_ID --all
85	ax datasets export NAME_OR_ID --version-id VERSION_ID
86	ax datasets export NAME_OR_ID --output-dir ./data
87	ax datasets export NAME_OR_ID --stdout
88	ax datasets export NAME_OR_ID --stdout \| jq '.[0]'
89	ax datasets export NAME_OR_ID --space SPACE # required when using dataset name instead of ID
90	```
91
92	### Flags
93
94	\| Flag \| Type \| Default \| Description \|
95	\|------\|------\|---------\|-------------\|
96	\| `NAME_OR_ID` \| string \| required \| Dataset name or ID (positional) \|
97	\| `--space` \| string \| none \| Space name or ID (required if using dataset name instead of ID) \|
98	\| `--version-id` \| string \| latest \| Export a specific dataset version \|
99	\| `--all` \| bool \| false \| Unlimited bulk export (use for datasets > 500 examples) \|
100	\| `--output-dir` \| s

People who liked this also viewed

6 picks

Type