aliyun-qwen-vl

Name: aliyun-qwen-vl
Author: cinience

69installs34forks

How to install aliyun-qwen-vl?

cinience/alicloud-skills/aliyun-qwen-vl

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-vl

Installs into the current project.

Summary

Use when understanding images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus/qwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart/table reading, or screenshot understanding workflows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen VL (Image Understanding)
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-vl
9	python -m py_compile skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py && echo "py_compile_ok" > output/aliyun-qwen-vl/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-vl/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save raw model responses and normalized extraction results to `output/aliyun-qwen-vl/`.
17	- Include input image reference and prompt for traceability.
18
19	Use Qwen VL models for image input + text output understanding tasks via DashScope compatible-mode API.
20
21	## Prerequisites
22
23	- Install dependencies (recommended in a venv):
24
25	```bash
26	python3 -m venv .venv
27	. .venv/bin/activate
28	python -m pip install requests
29	```
30
31	- Set `DASHSCOPE_API_KEY` in environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
32
33	## Critical model names
34
35	Prefer the Qwen3 VL family:
36	- `qwen3-vl-plus`
37	- `qwen3-vl-flash`
38
39	When you need explicit "latest" routing or reproducible snapshots, use supported aliases/snapshots from the official model list, such as:
40	- `qwen3-vl-plus-latest`
41	- `qwen3-vl-plus-2025-12-19`
42	- `qwen3-vl-flash-2026-01-22`
43	- `qwen3-vl-flash-latest`
44
45	Legacy names still seen in some workloads:
46	- `qwen-vl-max-latest`
47	- `qwen-vl-plus-latest`
48
49	For OCR-specialized extraction, prefer `skills/ai/multimodal/aliyun-qwen-ocr/` instead of using the general VL skill.
50
51	## Normalized interface (multimodal.chat)
52
53	### Request
54
55	- `prompt` (string, required): user question/instruction about image.
56	- `image` (string, required): HTTPS URL, local path, or `data:` URL.
57	- `model` (string, optional): default `qwen3-vl-plus`.
58	- `max_tokens` (int, optional): default `512`.
59	- `temperature` (float, optional): default `0.2`.
60	- `detail` (string, optional): `auto`/`low`/`high`, default `auto`.
61	- `json_mode` (bool, optional): return JSON-only response when possible.
62	- `schema` (object, optional): JSON Schema for structured extraction.
63	- `max_retries` (int, optional): retry count for `429/5xx`, default `2`.
64	- `retry_backoff_s` (float, optional): exponential backoff base seconds, default `1.5`.
65
66	### Response
67
68	- `text` (string): primary model answer.
69	- `model` (string): model actually used.
70	- `usage` (object): token usage if returned by backend.
71
72	## Quickstart
73
74	```bash
75	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
76	--request '{"prompt":"Summarize the main content in this image","image":"https://example.com/demo.jpg"}' \
77	--print-response
78	```
79
80	Using local image:
81
82	```bash
83	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
84	--request '{"prompt":"Extract key information from the image","image":"./samples/invoice.png","model":"qwen3-vl-plus"}' \
85	--print-response
86	```
87
88	Structured extraction (JSON mode):
89
90	```bash
91	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
92	--request '{"prompt":"Extract fields: title, amount, date","image":"./samples/invoice.png"}' \
93	--json-mode \
94	--print-response
95	```
96
97	Structured extraction (JSON Schema):
98
99	```bash
100	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
101	--request '{"prompt":"Extract invoice fields","image":"./samples/invoice.png"}' \
102	--schema skills/ai/multimodal/aliyun-qwen-vl/references/examples/invoice.schema.json \
103	--print-response
104	```
105
106	## cURL (compatible mode)
107
108	```bash
109	curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
110	-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
111	-H "Content-Type: application/json" \
112	-d '{
113	"model":"qwen3-vl-plus",
114	"messages":[
115	{
116	"role":"user",
117	"content":[
118	{"type":"image_url","image_url":{"url":"https://example.com/demo.jpg"}},
119	{"type":"text","text":"Describe this image and list executable actions"}
120	]
121	}
122	],
123	"max_tokens":512,
124	"temperature":0.2
125	}'
126	```
127
128	## Output location
129
130	- If `--output` is set, JSON response is saved to that file.
131	- Default output dir convention: `output/aliyun-qwen-vl/`.
132
133	## Smoke test
134
135	```bash
136	python tests/ai/multimodal/aliyun-qwen-vl-test/scripts/smoke_test_qwen_vl.py \
137	--image ./tmp/vl_test_cat.png
138	```
139
140	## Error handling
141
142	\| Error \| Likely cause \| Action \|
143	\| --- \| --- \| --- \|
144	\| 401/403 \| Missing or invalid key \| Check `DASHSCOPE_API_KEY` and account permissions. \|
145	\| 400 \| Invalid request schema or unsupported image source \| Validate `messages` content and image URL/path format. \|
146	\| 429 \| Rate limit \| Retry with exponential backoff and lower concurrency. \|
147	\| 5xx \| Temporary backend issue \| Retry with backoff and idempotent request design. \|
148
149	## Operational guidance
150
151	- For stable production behavio

People who liked this also viewed

6 picks

Type

aliyun-qwen-vl

69installs34forks

View on GitHub

How to install aliyun-qwen-vl?

cinience/alicloud-skills/aliyun-qwen-vl

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-vl

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen VL (Image Understanding)
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-vl
9	python -m py_compile skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py && echo "py_compile_ok" > output/aliyun-qwen-vl/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-vl/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save raw model responses and normalized extraction results to `output/aliyun-qwen-vl/`.
17	- Include input image reference and prompt for traceability.
18
19	Use Qwen VL models for image input + text output understanding tasks via DashScope compatible-mode API.
20
21	## Prerequisites
22
23	- Install dependencies (recommended in a venv):
24
25	```bash
26	python3 -m venv .venv
27	. .venv/bin/activate
28	python -m pip install requests
29	```
30
31	- Set `DASHSCOPE_API_KEY` in environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
32
33	## Critical model names
34
35	Prefer the Qwen3 VL family:
36	- `qwen3-vl-plus`
37	- `qwen3-vl-flash`
38
39	When you need explicit "latest" routing or reproducible snapshots, use supported aliases/snapshots from the official model list, such as:
40	- `qwen3-vl-plus-latest`
41	- `qwen3-vl-plus-2025-12-19`
42	- `qwen3-vl-flash-2026-01-22`
43	- `qwen3-vl-flash-latest`
44
45	Legacy names still seen in some workloads:
46	- `qwen-vl-max-latest`
47	- `qwen-vl-plus-latest`
48
49	For OCR-specialized extraction, prefer `skills/ai/multimodal/aliyun-qwen-ocr/` instead of using the general VL skill.
50
51	## Normalized interface (multimodal.chat)
52
53	### Request
54
55	- `prompt` (string, required): user question/instruction about image.
56	- `image` (string, required): HTTPS URL, local path, or `data:` URL.
57	- `model` (string, optional): default `qwen3-vl-plus`.
58	- `max_tokens` (int, optional): default `512`.
59	- `temperature` (float, optional): default `0.2`.
60	- `detail` (string, optional): `auto`/`low`/`high`, default `auto`.
61	- `json_mode` (bool, optional): return JSON-only response when possible.
62	- `schema` (object, optional): JSON Schema for structured extraction.
63	- `max_retries` (int, optional): retry count for `429/5xx`, default `2`.
64	- `retry_backoff_s` (float, optional): exponential backoff base seconds, default `1.5`.
65
66	### Response
67
68	- `text` (string): primary model answer.
69	- `model` (string): model actually used.
70	- `usage` (object): token usage if returned by backend.
71
72	## Quickstart
73
74	```bash
75	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
76	--request '{"prompt":"Summarize the main content in this image","image":"https://example.com/demo.jpg"}' \
77	--print-response
78	```
79
80	Using local image:
81
82	```bash
83	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
84	--request '{"prompt":"Extract key information from the image","image":"./samples/invoice.png","model":"qwen3-vl-plus"}' \
85	--print-response
86	```
87
88	Structured extraction (JSON mode):
89
90	```bash
91	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
92	--request '{"prompt":"Extract fields: title, amount, date","image":"./samples/invoice.png"}' \
93	--json-mode \
94	--print-response
95	```
96
97	Structured extraction (JSON Schema):
98
99	```bash
100	python skills/ai/multimodal/aliyun-qwen-vl/scripts/analyze_image.py \
101	--request '{"prompt":"Extract invoice fields","image":"./samples/invoice.png"}' \
102	--schema skills/ai/multimodal/aliyun-qwen-vl/references/examples/invoice.schema.json \
103	--print-response
104	```
105
106	## cURL (compatible mode)
107
108	```bash
109	curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
110	-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
111	-H "Content-Type: application/json" \
112	-d '{
113	"model":"qwen3-vl-plus",
114	"messages":[
115	{
116	"role":"user",
117	"content":[
118	{"type":"image_url","image_url":{"url":"https://example.com/demo.jpg"}},
119	{"type":"text","text":"Describe this image and list executable actions"}
120	]
121	}
122	],
123	"max_tokens":512,
124	"temperature":0.2
125	}'
126	```
127
128	## Output location
129
130	- If `--output` is set, JSON response is saved to that file.
131	- Default output dir convention: `output/aliyun-qwen-vl/`.
132
133	## Smoke test
134
135	```bash
136	python tests/ai/multimodal/aliyun-qwen-vl-test/scripts/smoke_test_qwen_vl.py \
137	--image ./tmp/vl_test_cat.png
138	```
139
140	## Error handling
141
142	\| Error \| Likely cause \| Action \|
143	\| --- \| --- \| --- \|
144	\| 401/403 \| Missing or invalid key \| Check `DASHSCOPE_API_KEY` and account permissions. \|
145	\| 400 \| Invalid request schema or unsupported image source \| Validate `messages` content and image URL/path format. \|
146	\| 429 \| Rate limit \| Retry with exponential backoff and lower concurrency. \|
147	\| 5xx \| Temporary backend issue \| Retry with backoff and idempotent request design. \|
148
149	## Operational guidance
150
151	- For stable production behavio

People who liked this also viewed

6 picks

Type