aliyun-docmind-extract

Name: aliyun-docmind-extract
Author: cinience

397stars34forks

How to install aliyun-docmind-extract?

cinience/alicloud-skills/aliyun-docmind-extract

$npx -y skills add cinience/alicloud-skills --skill aliyun-docmind-extract

Installs into the current project.

Summary

Use when working with Document Mind (DocMind) via Node.js SDK to submit document parsing jobs and poll results. Designed for Claude Code/Codex document understanding workflows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Document Mind (DocMind) — Node.js SDK
4
5	Use DocMind to extract document structure, text, and layout with async jobs.
6
7	## Prerequisites
8
9	- Install SDKs:
10	- `npm install @alicloud/docmind-api20220711 @alicloud/tea-util @alicloud/credentials`
11	- Provide credentials via standard Alibaba Cloud env vars:
12	- `ALIBABACLOUD_ACCESS_KEY_ID`
13	- `ALIBABACLOUD_ACCESS_KEY_SECRET`
14	- `ALIBABACLOUD_REGION_ID` (optional default; if unset, choose the most reasonable region for the task or ask the user)
15
16	## Quickstart (submit + poll)
17
18	```js
19	const Client = require('@alicloud/docmind-api20220711');
20	const Credential = require('@alicloud/credentials');
21	const Util = require('@alicloud/tea-util');
22
23	const cred = new Credential.default();
24	const regionId =
25	process.env.ALIBABACLOUD_REGION_ID \|\|
26	process.env.ALIBABA_CLOUD_REGION_ID \|\|
27	process.env.ALICLOUD_REGION_ID \|\|
28	'cn-hangzhou'; // Example default; choose/ask if unset.
29	const client = new Client.default({
30	endpoint: `docmind-api.${regionId}.aliyuncs.com`,
31	accessKeyId: cred.credential.accessKeyId,
32	accessKeySecret: cred.credential.accessKeySecret,
33	type: 'access_key',
34	regionId,
35	});
36
37	async function submitByUrl(fileUrl, fileName) {
38	const req = new Client.SubmitDocStructureJobRequest();
39	req.fileUrl = fileUrl;
40	req.fileName = fileName;
41	const resp = await client.submitDocStructureJob(req);
42	return resp.body.data.id;
43	}
44
45	async function pollResult(jobId) {
46	const req = new Client.GetDocStructureResultRequest();
47	req.id = jobId;
48	const resp = await client.getDocStructureResult(req);
49	return resp.body;
50	}
51
52	(async () => {
53	const jobId = await submitByUrl('https://example.com/example.pdf', 'example.pdf');
54	console.log('jobId:', jobId);
55
56	// Poll every 10s until completed.
57	for (;;) {
58	const result = await pollResult(jobId);
59	if (result.completed) {
60	console.log(result.status, result.data \|\| result.message);
61	break;
62	}
63	await new Promise((r) => setTimeout(r, 10000));
64	}
65	})();
66	```
67
68	## Script quickstart
69
70	```bash
71	DOCMIND_FILE_URL="https://example.com/example.pdf" \\
72	node skills/ai/text/aliyun-docmind-extract/scripts/quickstart.js
73	```
74
75	Environment variables:
76
77	- `DOCMIND_FILE_URL`
78	- `DOCMIND_FILE_NAME` (optional)
79	- `DOCMIND_POLL_INTERVAL_MS` (optional, default 10000)
80	- `DOCMIND_MAX_POLLS` (optional, default 120)
81
82	## Local file upload
83
84	```js
85	const fs = require('fs');
86	const advanceReq = new Client.SubmitDocStructureJobAdvanceRequest();
87	advanceReq.fileUrlObject = fs.createReadStream('./example.pdf');
88	advanceReq.fileName = 'example.pdf';
89	const runtime = new Util.RuntimeOptions({});
90	const resp = await client.submitDocStructureJobAdvance(advanceReq, runtime);
91	```
92
93	## Notes for Claude Code/Codex
94
95	- DocMind is async: submit a job, then poll until `completed=true`.
96	- Poll every ~10s; max processing window is 120 minutes.
97	- Keep files publicly accessible when using URL submission.
98
99	## Error handling
100
101	- `UrlNotLegal`: URL not publicly accessible or malformed.
102	- `DocProcessing`: job still running; keep polling.
103	- `Fail`: check `message` and error code for root cause.
104
105	## Validation
106
107	```bash
108	mkdir -p output/aliyun-docmind-extract
109	for f in skills/ai/text/aliyun-docmind-extract/scripts/*.py; do
110	python3 -m py_compile "$f"
111	done
112	echo "py_compile_ok" > output/aliyun-docmind-extract/validate.txt
113	```
114
115	Pass criteria: command exits 0 and `output/aliyun-docmind-extract/validate.txt` is generated.
116
117	## Output And Evidence
118
119	- Save artifacts, command outputs, and API response summaries under `output/aliyun-docmind-extract/`.
120	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
121
122	## Workflow
123
124	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
125	2) Run one minimal read-only query first to verify connectivity and permissions.
126	3) Execute the target operation with explicit parameters and bounded scope.
127	4) Verify results and save output/evidence files.
128
129	## References
130
131	- DocMind Node.js SDK: `@alicloud/docmind-api20220711`
132
133	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-docmind-extract

397stars34forks

View on GitHub

How to install aliyun-docmind-extract?

cinience/alicloud-skills/aliyun-docmind-extract

$npx -y skills add cinience/alicloud-skills --skill aliyun-docmind-extract

Installs into the current project.

Summary

Use when working with Document Mind (DocMind) via Node.js SDK to submit document parsing jobs and poll results. Designed for Claude Code/Codex document understanding workflows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Document Mind (DocMind) — Node.js SDK
4
5	Use DocMind to extract document structure, text, and layout with async jobs.
6
7	## Prerequisites
8
9	- Install SDKs:
10	- `npm install @alicloud/docmind-api20220711 @alicloud/tea-util @alicloud/credentials`
11	- Provide credentials via standard Alibaba Cloud env vars:
12	- `ALIBABACLOUD_ACCESS_KEY_ID`
13	- `ALIBABACLOUD_ACCESS_KEY_SECRET`
14	- `ALIBABACLOUD_REGION_ID` (optional default; if unset, choose the most reasonable region for the task or ask the user)
15
16	## Quickstart (submit + poll)
17
18	```js
19	const Client = require('@alicloud/docmind-api20220711');
20	const Credential = require('@alicloud/credentials');
21	const Util = require('@alicloud/tea-util');
22
23	const cred = new Credential.default();
24	const regionId =
25	process.env.ALIBABACLOUD_REGION_ID \|\|
26	process.env.ALIBABA_CLOUD_REGION_ID \|\|
27	process.env.ALICLOUD_REGION_ID \|\|
28	'cn-hangzhou'; // Example default; choose/ask if unset.
29	const client = new Client.default({
30	endpoint: `docmind-api.${regionId}.aliyuncs.com`,
31	accessKeyId: cred.credential.accessKeyId,
32	accessKeySecret: cred.credential.accessKeySecret,
33	type: 'access_key',
34	regionId,
35	});
36
37	async function submitByUrl(fileUrl, fileName) {
38	const req = new Client.SubmitDocStructureJobRequest();
39	req.fileUrl = fileUrl;
40	req.fileName = fileName;
41	const resp = await client.submitDocStructureJob(req);
42	return resp.body.data.id;
43	}
44
45	async function pollResult(jobId) {
46	const req = new Client.GetDocStructureResultRequest();
47	req.id = jobId;
48	const resp = await client.getDocStructureResult(req);
49	return resp.body;
50	}
51
52	(async () => {
53	const jobId = await submitByUrl('https://example.com/example.pdf', 'example.pdf');
54	console.log('jobId:', jobId);
55
56	// Poll every 10s until completed.
57	for (;;) {
58	const result = await pollResult(jobId);
59	if (result.completed) {
60	console.log(result.status, result.data \|\| result.message);
61	break;
62	}
63	await new Promise((r) => setTimeout(r, 10000));
64	}
65	})();
66	```
67
68	## Script quickstart
69
70	```bash
71	DOCMIND_FILE_URL="https://example.com/example.pdf" \\
72	node skills/ai/text/aliyun-docmind-extract/scripts/quickstart.js
73	```
74
75	Environment variables:
76
77	- `DOCMIND_FILE_URL`
78	- `DOCMIND_FILE_NAME` (optional)
79	- `DOCMIND_POLL_INTERVAL_MS` (optional, default 10000)
80	- `DOCMIND_MAX_POLLS` (optional, default 120)
81
82	## Local file upload
83
84	```js
85	const fs = require('fs');
86	const advanceReq = new Client.SubmitDocStructureJobAdvanceRequest();
87	advanceReq.fileUrlObject = fs.createReadStream('./example.pdf');
88	advanceReq.fileName = 'example.pdf';
89	const runtime = new Util.RuntimeOptions({});
90	const resp = await client.submitDocStructureJobAdvance(advanceReq, runtime);
91	```
92
93	## Notes for Claude Code/Codex
94
95	- DocMind is async: submit a job, then poll until `completed=true`.
96	- Poll every ~10s; max processing window is 120 minutes.
97	- Keep files publicly accessible when using URL submission.
98
99	## Error handling
100
101	- `UrlNotLegal`: URL not publicly accessible or malformed.
102	- `DocProcessing`: job still running; keep polling.
103	- `Fail`: check `message` and error code for root cause.
104
105	## Validation
106
107	```bash
108	mkdir -p output/aliyun-docmind-extract
109	for f in skills/ai/text/aliyun-docmind-extract/scripts/*.py; do
110	python3 -m py_compile "$f"
111	done
112	echo "py_compile_ok" > output/aliyun-docmind-extract/validate.txt
113	```
114
115	Pass criteria: command exits 0 and `output/aliyun-docmind-extract/validate.txt` is generated.
116
117	## Output And Evidence
118
119	- Save artifacts, command outputs, and API response summaries under `output/aliyun-docmind-extract/`.
120	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
121
122	## Workflow
123
124	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
125	2) Run one minimal read-only query first to verify connectivity and permissions.
126	3) Execute the target operation with explicit parameters and bounded scope.
127	4) Verify results and save output/evidence files.
128
129	## References
130
131	- DocMind Node.js SDK: `@alicloud/docmind-api20220711`
132
133	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type