aliyun-opensearch-search

Name: aliyun-opensearch-search
Author: cinience

49installs34forks

How to install aliyun-opensearch-search?

cinience/alicloud-skills/aliyun-opensearch-search

$npx -y skills add cinience/alicloud-skills --skill aliyun-opensearch-search

Installs into the current project.

Summary

Use when working with OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches. Ideal for RAG and vector retrieval pipelines in Claude Code/Codex.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# OpenSearch Vector Search Edition
4
5	Use the ha3engine SDK to push documents and execute HA/SQL searches. This skill focuses on API/SDK usage only (no console steps).
6
7	## Prerequisites
8
9	- Install SDK (recommended in a venv to avoid PEP 668 limits):
10
11	```bash
12	python3 -m venv .venv
13	. .venv/bin/activate
14	python -m pip install alibabacloud-ha3engine
15	```
16	- Provide connection config via environment variables:
17	- `OPENSEARCH_ENDPOINT` (API domain)
18	- `OPENSEARCH_INSTANCE_ID`
19	- `OPENSEARCH_USERNAME`
20	- `OPENSEARCH_PASSWORD`
21	- `OPENSEARCH_DATASOURCE` (data source name)
22	- `OPENSEARCH_PK_FIELD` (primary key field name)
23
24	## Quickstart (push + search)
25
26	```python
27	import os
28	from alibabacloud_ha3engine import models, client
29	from Tea.exceptions import TeaException, RetryError
30
31	cfg = models.Config(
32	endpoint=os.getenv("OPENSEARCH_ENDPOINT"),
33	instance_id=os.getenv("OPENSEARCH_INSTANCE_ID"),
34	protocol="http",
35	access_user_name=os.getenv("OPENSEARCH_USERNAME"),
36	access_pass_word=os.getenv("OPENSEARCH_PASSWORD"),
37	)
38	ha3 = client.Client(cfg)
39
40	def push_docs():
41	data_source = os.getenv("OPENSEARCH_DATASOURCE")
42	pk_field = os.getenv("OPENSEARCH_PK_FIELD", "id")
43
44	documents = [
45	{"fields": {"id": 1, "title": "hello", "content": "world"}, "cmd": "add"},
46	{"fields": {"id": 2, "title": "faq", "content": "vector search"}, "cmd": "add"},
47	]
48	req = models.PushDocumentsRequestModel({}, documents)
49	return ha3.push_documents(data_source, pk_field, req)
50
51
52	def search_ha():
53	# HA query example. Replace cluster/table names as needed.
54	query_str = (
55	"config=hit:5,format:json,qrs_chain:search"
56	"&&query=title:hello"
57	"&&cluster=general"
58	)
59	ha_query = models.SearchQuery(query=query_str)
60	req = models.SearchRequestModel({}, ha_query)
61	return ha3.search(req)
62
63	try:
64	print(push_docs().body)
65	print(search_ha())
66	except (TeaException, RetryError) as e:
67	print(e)
68	```
69
70	## Script quickstart
71
72	```bash
73	python skills/ai/search/aliyun-opensearch-search/scripts/quickstart.py
74	```
75
76	Environment variables:
77
78	- `OPENSEARCH_ENDPOINT`
79	- `OPENSEARCH_INSTANCE_ID`
80	- `OPENSEARCH_USERNAME`
81	- `OPENSEARCH_PASSWORD`
82	- `OPENSEARCH_DATASOURCE`
83	- `OPENSEARCH_PK_FIELD` (optional, default `id`)
84	- `OPENSEARCH_CLUSTER` (optional, default `general`)
85
86	Optional args: `--cluster`, `--hit`, `--query`.
87
88	## SQL-style search
89
90	```python
91	from alibabacloud_ha3engine import models
92
93	sql = "select * from <indexTableName>&&kvpair=trace:INFO;formatType:json"
94	sql_query = models.SearchQuery(sql=sql)
95	req = models.SearchRequestModel({}, sql_query)
96	resp = ha3.search(req)
97	print(resp)
98	```
99
100	## Notes for Claude Code/Codex
101
102	- Use `push_documents` for add/delete updates.
103	- Large query strings (>30KB) should use the RESTful search API.
104	- HA queries are fast and flexible for vector + keyword retrieval; SQL is helpful for structured data.
105
106	## Error handling
107
108	- Auth errors: verify username/password and instance access.
109	- 4xx on push: check schema fields and `pk_field` alignment.
110	- 5xx: retry with backoff.
111
112	## Validation
113
114	```bash
115	mkdir -p output/aliyun-opensearch-search
116	for f in skills/ai/search/aliyun-opensearch-search/scripts/*.py; do
117	python3 -m py_compile "$f"
118	done
119	echo "py_compile_ok" > output/aliyun-opensearch-search/validate.txt
120	```
121
122	Pass criteria: command exits 0 and `output/aliyun-opensearch-search/validate.txt` is generated.
123
124	## Output And Evidence
125
126	- Save artifacts, command outputs, and API response summaries under `output/aliyun-opensearch-search/`.
127	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
128
129	## Workflow
130
131	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
132	2) Run one minimal read-only query first to verify connectivity and permissions.
133	3) Execute the target operation with explicit parameters and bounded scope.
134	4) Verify results and save output/evidence files.
135
136	## References
137
138	- SDK package: `alibabacloud-ha3engine`
139	- Demos: data push and HA/SQL search demos in OpenSearch docs
140
141	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-opensearch-search

49installs34forks

View on GitHub

How to install aliyun-opensearch-search?

cinience/alicloud-skills/aliyun-opensearch-search

$npx -y skills add cinience/alicloud-skills --skill aliyun-opensearch-search

Installs into the current project.

Summary

Use when working with OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches. Ideal for RAG and vector retrieval pipelines in Claude Code/Codex.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# OpenSearch Vector Search Edition
4
5	Use the ha3engine SDK to push documents and execute HA/SQL searches. This skill focuses on API/SDK usage only (no console steps).
6
7	## Prerequisites
8
9	- Install SDK (recommended in a venv to avoid PEP 668 limits):
10
11	```bash
12	python3 -m venv .venv
13	. .venv/bin/activate
14	python -m pip install alibabacloud-ha3engine
15	```
16	- Provide connection config via environment variables:
17	- `OPENSEARCH_ENDPOINT` (API domain)
18	- `OPENSEARCH_INSTANCE_ID`
19	- `OPENSEARCH_USERNAME`
20	- `OPENSEARCH_PASSWORD`
21	- `OPENSEARCH_DATASOURCE` (data source name)
22	- `OPENSEARCH_PK_FIELD` (primary key field name)
23
24	## Quickstart (push + search)
25
26	```python
27	import os
28	from alibabacloud_ha3engine import models, client
29	from Tea.exceptions import TeaException, RetryError
30
31	cfg = models.Config(
32	endpoint=os.getenv("OPENSEARCH_ENDPOINT"),
33	instance_id=os.getenv("OPENSEARCH_INSTANCE_ID"),
34	protocol="http",
35	access_user_name=os.getenv("OPENSEARCH_USERNAME"),
36	access_pass_word=os.getenv("OPENSEARCH_PASSWORD"),
37	)
38	ha3 = client.Client(cfg)
39
40	def push_docs():
41	data_source = os.getenv("OPENSEARCH_DATASOURCE")
42	pk_field = os.getenv("OPENSEARCH_PK_FIELD", "id")
43
44	documents = [
45	{"fields": {"id": 1, "title": "hello", "content": "world"}, "cmd": "add"},
46	{"fields": {"id": 2, "title": "faq", "content": "vector search"}, "cmd": "add"},
47	]
48	req = models.PushDocumentsRequestModel({}, documents)
49	return ha3.push_documents(data_source, pk_field, req)
50
51
52	def search_ha():
53	# HA query example. Replace cluster/table names as needed.
54	query_str = (
55	"config=hit:5,format:json,qrs_chain:search"
56	"&&query=title:hello"
57	"&&cluster=general"
58	)
59	ha_query = models.SearchQuery(query=query_str)
60	req = models.SearchRequestModel({}, ha_query)
61	return ha3.search(req)
62
63	try:
64	print(push_docs().body)
65	print(search_ha())
66	except (TeaException, RetryError) as e:
67	print(e)
68	```
69
70	## Script quickstart
71
72	```bash
73	python skills/ai/search/aliyun-opensearch-search/scripts/quickstart.py
74	```
75
76	Environment variables:
77
78	- `OPENSEARCH_ENDPOINT`
79	- `OPENSEARCH_INSTANCE_ID`
80	- `OPENSEARCH_USERNAME`
81	- `OPENSEARCH_PASSWORD`
82	- `OPENSEARCH_DATASOURCE`
83	- `OPENSEARCH_PK_FIELD` (optional, default `id`)
84	- `OPENSEARCH_CLUSTER` (optional, default `general`)
85
86	Optional args: `--cluster`, `--hit`, `--query`.
87
88	## SQL-style search
89
90	```python
91	from alibabacloud_ha3engine import models
92
93	sql = "select * from <indexTableName>&&kvpair=trace:INFO;formatType:json"
94	sql_query = models.SearchQuery(sql=sql)
95	req = models.SearchRequestModel({}, sql_query)
96	resp = ha3.search(req)
97	print(resp)
98	```
99
100	## Notes for Claude Code/Codex
101
102	- Use `push_documents` for add/delete updates.
103	- Large query strings (>30KB) should use the RESTful search API.
104	- HA queries are fast and flexible for vector + keyword retrieval; SQL is helpful for structured data.
105
106	## Error handling
107
108	- Auth errors: verify username/password and instance access.
109	- 4xx on push: check schema fields and `pk_field` alignment.
110	- 5xx: retry with backoff.
111
112	## Validation
113
114	```bash
115	mkdir -p output/aliyun-opensearch-search
116	for f in skills/ai/search/aliyun-opensearch-search/scripts/*.py; do
117	python3 -m py_compile "$f"
118	done
119	echo "py_compile_ok" > output/aliyun-opensearch-search/validate.txt
120	```
121
122	Pass criteria: command exits 0 and `output/aliyun-opensearch-search/validate.txt` is generated.
123
124	## Output And Evidence
125
126	- Save artifacts, command outputs, and API response summaries under `output/aliyun-opensearch-search/`.
127	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
128
129	## Workflow
130
131	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
132	2) Run one minimal read-only query first to verify connectivity and permissions.
133	3) Execute the target operation with explicit parameters and bounded scope.
134	4) Verify results and save output/evidence files.
135
136	## References
137
138	- SDK package: `alibabacloud-ha3engine`
139	- Demos: data push and HA/SQL search demos in OpenSearch docs
140
141	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type