aliyun-milvus-search

Name: aliyun-milvus-search
Author: cinience

51installs34forks

How to install aliyun-milvus-search?

cinience/alicloud-skills/aliyun-milvus-search

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

Installs into the current project.

Summary

Use when working with AliCloud Milvus (serverless) with PyMilvus to create collections, insert vectors, and run filtered similarity search. Optimized for Claude Code/Codex vector retrieval flows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# AliCloud Milvus (Serverless) via PyMilvus
4
5	This skill uses standard PyMilvus APIs to connect to AliCloud Milvus and run vector search.
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 --upgrade pymilvus
15	```
16	- Provide connection via environment variables:
17	- `MILVUS_URI` (e.g. `http://<host>:19530`)
18	- `MILVUS_TOKEN` (`<username>:<password>`)
19	- `MILVUS_DB` (default: `default`)
20
21	## Quickstart (Python)
22
23	```python
24	import os
25	from pymilvus import MilvusClient
26
27	client = MilvusClient(
28	uri=os.getenv("MILVUS_URI"),
29	token=os.getenv("MILVUS_TOKEN"),
30	db_name=os.getenv("MILVUS_DB", "default"),
31	)
32
33	# 1) Create a collection
34	client.create_collection(
35	collection_name="docs",
36	dimension=768,
37	)
38
39	# 2) Insert data
40	items = [
41	{"id": 1, "vector": [0.01] * 768, "source": "kb", "chunk": 0},
42	{"id": 2, "vector": [0.02] * 768, "source": "kb", "chunk": 1},
43	]
44	client.insert(collection_name="docs", data=items)
45
46	# 3) Search
47	query_vectors = [[0.01] * 768]
48	res = client.search(
49	collection_name="docs",
50	data=query_vectors,
51	limit=5,
52	filter='source == "kb" and chunk >= 0',
53	output_fields=["source", "chunk"],
54	)
55	print(res)
56	```
57
58	## Script quickstart
59
60	```bash
61	python skills/ai/search/aliyun-milvus-search/scripts/quickstart.py
62	```
63
64	Environment variables:
65
66	- `MILVUS_URI`
67	- `MILVUS_TOKEN`
68	- `MILVUS_DB` (optional)
69	- `MILVUS_COLLECTION` (optional)
70	- `MILVUS_DIMENSION` (optional)
71
72	Optional args: `--collection`, `--dimension`, `--limit`, `--filter`.
73
74	## Notes for Claude Code/Codex
75
76	- Insert is async; wait a few seconds before searching newly inserted data.
77	- Keep vector `dimension` aligned with your embedding model.
78	- Use filters to enforce tenant scoping or dataset partitions.
79
80	## Error handling
81
82	- Auth errors: check `MILVUS_TOKEN` and instance permissions.
83	- Dimension mismatch: ensure all vectors match collection dimension.
84	- Network errors: verify VPC/public access settings on the instance.
85
86	## Validation
87
88	```bash
89	mkdir -p output/aliyun-milvus-search
90	for f in skills/ai/search/aliyun-milvus-search/scripts/*.py; do
91	python3 -m py_compile "$f"
92	done
93	echo "py_compile_ok" > output/aliyun-milvus-search/validate.txt
94	```
95
96	Pass criteria: command exits 0 and `output/aliyun-milvus-search/validate.txt` is generated.
97
98	## Output And Evidence
99
100	- Save artifacts, command outputs, and API response summaries under `output/aliyun-milvus-search/`.
101	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
102
103	## Workflow
104
105	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
106	2) Run one minimal read-only query first to verify connectivity and permissions.
107	3) Execute the target operation with explicit parameters and bounded scope.
108	4) Verify results and save output/evidence files.
109
110	## References
111
112	- PyMilvus `MilvusClient` examples for AliCloud Milvus
113
114	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-milvus-search

51installs34forks

View on GitHub

How to install aliyun-milvus-search?

cinience/alicloud-skills/aliyun-milvus-search

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

Installs into the current project.

Summary

Use when working with AliCloud Milvus (serverless) with PyMilvus to create collections, insert vectors, and run filtered similarity search. Optimized for Claude Code/Codex vector retrieval flows.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# AliCloud Milvus (Serverless) via PyMilvus
4
5	This skill uses standard PyMilvus APIs to connect to AliCloud Milvus and run vector search.
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 --upgrade pymilvus
15	```
16	- Provide connection via environment variables:
17	- `MILVUS_URI` (e.g. `http://<host>:19530`)
18	- `MILVUS_TOKEN` (`<username>:<password>`)
19	- `MILVUS_DB` (default: `default`)
20
21	## Quickstart (Python)
22
23	```python
24	import os
25	from pymilvus import MilvusClient
26
27	client = MilvusClient(
28	uri=os.getenv("MILVUS_URI"),
29	token=os.getenv("MILVUS_TOKEN"),
30	db_name=os.getenv("MILVUS_DB", "default"),
31	)
32
33	# 1) Create a collection
34	client.create_collection(
35	collection_name="docs",
36	dimension=768,
37	)
38
39	# 2) Insert data
40	items = [
41	{"id": 1, "vector": [0.01] * 768, "source": "kb", "chunk": 0},
42	{"id": 2, "vector": [0.02] * 768, "source": "kb", "chunk": 1},
43	]
44	client.insert(collection_name="docs", data=items)
45
46	# 3) Search
47	query_vectors = [[0.01] * 768]
48	res = client.search(
49	collection_name="docs",
50	data=query_vectors,
51	limit=5,
52	filter='source == "kb" and chunk >= 0',
53	output_fields=["source", "chunk"],
54	)
55	print(res)
56	```
57
58	## Script quickstart
59
60	```bash
61	python skills/ai/search/aliyun-milvus-search/scripts/quickstart.py
62	```
63
64	Environment variables:
65
66	- `MILVUS_URI`
67	- `MILVUS_TOKEN`
68	- `MILVUS_DB` (optional)
69	- `MILVUS_COLLECTION` (optional)
70	- `MILVUS_DIMENSION` (optional)
71
72	Optional args: `--collection`, `--dimension`, `--limit`, `--filter`.
73
74	## Notes for Claude Code/Codex
75
76	- Insert is async; wait a few seconds before searching newly inserted data.
77	- Keep vector `dimension` aligned with your embedding model.
78	- Use filters to enforce tenant scoping or dataset partitions.
79
80	## Error handling
81
82	- Auth errors: check `MILVUS_TOKEN` and instance permissions.
83	- Dimension mismatch: ensure all vectors match collection dimension.
84	- Network errors: verify VPC/public access settings on the instance.
85
86	## Validation
87
88	```bash
89	mkdir -p output/aliyun-milvus-search
90	for f in skills/ai/search/aliyun-milvus-search/scripts/*.py; do
91	python3 -m py_compile "$f"
92	done
93	echo "py_compile_ok" > output/aliyun-milvus-search/validate.txt
94	```
95
96	Pass criteria: command exits 0 and `output/aliyun-milvus-search/validate.txt` is generated.
97
98	## Output And Evidence
99
100	- Save artifacts, command outputs, and API response summaries under `output/aliyun-milvus-search/`.
101	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
102
103	## Workflow
104
105	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
106	2) Run one minimal read-only query first to verify connectivity and permissions.
107	3) Execute the target operation with explicit parameters and bounded scope.
108	4) Verify results and save output/evidence files.
109
110	## References
111
112	- PyMilvus `MilvusClient` examples for AliCloud Milvus
113
114	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type