Leverage multimodal AI models to extract semantic descriptions and concise summaries from images, videos, audio, and documents stored in OSS Buckets. Build searchable vector indexes to enable advanced retrieval capabilities such as text-to-image and text-to-video search.
Prerequisites
Aliyun CLI (>= 3.3.3)
Pre-check: Aliyun CLI >= 3.3.3 required
This skill uses Aliyun CLI for all OSS operations except opening MetaQuery.
If Aliyun CLI is already installed, ossutil does not need to be installed separately.
Run the following command to verify the version: aliyun version
If not installed or the version is below 3.3.3,
run curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash to install/update,
or refer to references/cli-installation-guide.md for installation instructions.
Then [MUST] run aliyun configure set --auto-plugin-install true to enable automatic plugin installation.
[MUST] run aliyun plugin update to ensure that any existing plugins on your local machine are always up-to-date.
Update the aliyun ossutil plugin
Troubleshooting: --user-agent unknown flag error
If you encounter Error: unknown flag: --user-agent when running a command, the ossutil plugin version is too old. Run the following command to update to the latest version:
Required: Aliyun CLI, Python dependencies oss2 and alibabacloud-credentials
Not required: ossutil
The only operation that requires Python: opening MetaQuery (AI Content Awareness + semantic search)
Security Rules:
NEVER read, echo, or print AK/SK values (e.g., echo $ALIBABA_CLOUD_ACCESS_KEY_ID is FORBIDDEN)
NEVER ask the user to input AK/SK directly in the conversation or command line
At the start of the Core Workflow (before any CLI invocation):
[MUST] Enable AI-Mode — AI-mode is required for Agent Skill execution.
Run the following commands before any CLI invocation:
[MUST] Disable AI-Mode at EVERY exit point — Before delivering the final response for ANY reason, always disable AI-mode first. This applies to ALL exit paths: workflow success, workflow failure, error/exception, user cancellation, session end, or any other scenario where no further CLI commands will be executed.
AI-mode is only used for Agent Skill invocation scenarios and MUST NOT remain enabled after the skill stops running.
bash
aliyun configure ai-mode disable
[MUST] CLI User-Agent — Every aliyun CLI command invocation must include:
--user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
Note: If the user's Bucket is in a region not listed above, vector-mode MetaQuery and content awareness cannot be enabled, and an EC Code 0037-00000001 error will be returned. Guide the user to create a new Bucket in a supported region.
File Types
Supported: Images, videos, audio, documents
Multipart uploads: Only objects that have been assembled via CompleteMultipartUpload are shown
Performance Reference
OSS Internal Bandwidth and QPS
Region
Internal Bandwidth
Default QPS
cn-beijing, cn-hangzhou, cn-shanghai, cn-shenzhen
10Gbps
1250
Other regions
1Gbps
1250
This bandwidth and QPS is provided exclusively for vector search and does not consume the Bucket's QoS quota.
Existing File Index Build Time
File Type
10 Million Files
100 Million Files
1 Billion Files
Structured data & images
2-3 hours
1 day
~10 days
Videos, documents, audio
2-3 days
7-9 days
-
Incremental Updates and Search Latency
Incremental updates: When QPS < 1250, latency is typically minutes to hours
Delete Object: aliyun ossutil rm oss://<bucket-name>/<object-key> --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery -- Deletes a specific file
Batch Delete Objects: aliyun ossutil rm oss://<bucket-name>/ --recursive --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery -- Recursively deletes all files in the Bucket
Close MetaQuery: aliyun ossutil api close-meta-query --bucket <bucket-name> --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery -- Closes the metadata index; all indexed data will be cleared
Open MetaQuery: python scripts/open_metaquery.py --region <your-region> --bucket <your-bucket-name> --endpoint <your-endpoint> -- Opens the metadata index; existing data will start being indexed. If the bucket has more than 1000 objects, confirm with the user first.
Create Bucket: aliyun ossutil api put-bucket --bucket <bucket> --region <region-id> --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery -- Creates a Bucket
When confirming, explain the following to the user:
The specific operation to be performed
The scope of impact (which files/resources will be deleted or closed)
Whether the operation is reversible (most delete operations are irreversible)
Reason: Only the Python script or SDK can correctly configure WorkflowParameters to enable AI Content Awareness (ImageInsightEnable and VideoInsightEnable). Without this, semantic search quality will be severely degraded.
Rule 2: Must ask the user when Bucket name conflicts
When creating a Bucket and encountering a BucketAlreadyExists error:
Immediately stop all subsequent operations
Inform the user: "The Bucket name is already taken"
Ask the user to choose:
Option 1: Use the existing bucket (requires explicit user confirmation)
Option 2: Choose a new bucket name (user provides the new name)
Wait for the user's response before continuing
PROHIBITED:
Automatically modifying the bucket name (e.g., appending -2, -new, etc.)
Using an existing bucket without asking the user
Rule 3: Use Aliyun CLI by default for all operations except opening MetaQuery
The following operations should use Aliyun CLI by default:
Create Bucket
Query Bucket info
Query Bucket statistics
Upload files
Query MetaQuery status
Execute semantic search
Close MetaQuery
Delete Object / Bucket
Goal: Use the aliyun command uniformly, minimizing dependency on ossutil.
Rule 4: If Aliyun CLI is installed, ossutil is not needed
This skill does not require ossutil to be installed by default.
As long as Aliyun CLI >= 3.3.3 is installed and the following has been executed:
bash
aliyun configure set --auto-plugin-install true
It can be used as the default execution tool.
Core Workflows
Task 1: Create Bucket and Upload Files
Always confirm with the user before creating a bucket. Proceed only after the user agrees.
Task 2: Enable Vector Search & AI Content Awareness (Python script or SDK only)
WARNING: You MUST use python scripts/open_metaquery.py to open MetaQuery. Using aliyun ossutil api open-meta-query is STRICTLY PROHIBITED (it cannot configure WorkflowParameters, which prevents enabling AI Content Awareness features ImageInsightEnable and VideoInsightEnable, severely degrading semantic search quality).
Using the Python Script (Mandatory)
Before executing the Python script, complete the following environment setup:
2. Configure credentials:
The Python script uses the alibabacloud-credentials default credential chain to automatically discover credentials (supporting environment variables, ~/.aliyun/config.json, ECS instance roles, etc.). No explicit AK/SK handling is needed in the code. Ensure credentials are configured via the aliyun configure command.
3. Verify RAM permissions:
Users must have the minimum RAM permissions required for MetaQuery. See references/ram-policies.md.
If the user encounters an AccessDenied error, check that RAM permissions are correctly configured.
Enablement Process:
Prepare the Bucket:
a. If the user requests creating a new Bucket:
Run aliyun ossutil api put-bucket --bucket examplebucket --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery with the user-specified bucket name
If creation fails with a BucketAlreadyExists error:
Immediately stop the operation
Inform the user: "The Bucket name <bucket-name> is already taken (it may have been created by you or another user)"
You MUST ask the user: "Would you like to: 1) Use this existing bucket? or 2) Choose a new bucket name?"
Wait for the user's explicit response before continuing. Do not modify the bucket name or use the existing bucket without permission.
b. If the user provides an existing bucket:
First verify the bucket exists using aliyun ossutil api get-bucket-info --bucket <bucket-name> --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
If it does not exist, ask the user whether to create it
Verify Bucket object count: After the user provides a bucket, check the object count. If it exceeds 1000, warn the user that enabling MetaQuery will incur costs.
Use the following command to get the bucket's object count:
bash
aliyun ossutil api get-bucket-stat --bucket <your-bucket-name> --output-format json --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
The ObjectCount field in the response indicates the number of objects.
If the object count exceeds 1000, warn the user that enabling MetaQuery will incur costs and confirm whether to proceed.
If the object count is 0, ask the user which files to upload. Upload command:
bash
If MetaQueryMode=semantic and both VideoInsightEnable and ImageInsightEnable are True, the user has successfully enabled MetaQuery in vector mode with content awareness (which greatly improves semantic search quality). No further action is needed.
If these conditions are not met, recommend the user switch to a different bucket and start over.
Task 3: Execute Semantic Search
Prerequisites for MetaQuery Search
Before using MetaQuery for search, confirm the following:
Verify MetaQuery is enabled:
bash
aliyun ossutil api get-meta-query-status --bucket <your-bucket-name> --output-format json --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
If MetaQuery is not enabled: Complete the enablement process first. Refer to Task 2 to enable it using the Python script.
Check index scan status: The Phase field from get-meta-query-status indicates the current scan phase:
FullScanning: Full scan in progress. Search is not available yet. Wait for the full scan to complete.
IncrementalScanning: Incremental scan in progress. The index has been largely built and search can be performed normally.
Verify MetaQuery state is Running: MetaQuery is only available when State is Running. If the state is Ready or any non-Running state, you may need to wait or re-enable it.
1. Prepare the meta-query.xml file:
Create a meta-query.xml file to define query conditions. For detailed format, field descriptions, and complete examples, see references/metaquery.md.
Example of semantic vector search for video files containing "person" (MediaTypes can only be one of: video, image, audio, document):
2. Execute the search command:
This example uses semantic vector search. The meta-query.xml file defines the query conditions, and search results return the most similar files.
3. Optimizing search result display:
After search completes, when displaying results to the user, use the x-oss-process parameter to generate preview images or cover frames for image and video files, making it easier for the user to visually review search results. If the user's current channel supports multimedia files, send them directly to the user.
Note: The aliyun ossutil presign command generates a signed temporary access URL that can be opened directly in a browser for preview during its validity period. For image files, you can also add image processing parameters via x-oss-process (e.g., resize, crop):
This generates a thumbnail preview to reduce loading time.
Troubleshooting MetaQuery Search Issues
User asks "Why wasn't a specific file found?"
When a user reports that a specific uploaded file is missing from search results, troubleshoot based on the MetaQuery configuration:
a. Content awareness is NOT enabled:
If the user's MetaQuery does not have content awareness enabled (i.e., VideoInsightEnable or ImageInsightEnable is not True in WorkflowParameters), possible reasons include:
The file's metadata index has not been fully built yet. Wait for the index scan to complete (check the Phase field via aliyun ossutil api get-meta-query-status --bucket <bucket-name> --output-format json --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery).
Without content awareness, search is based only on basic file metadata (filename, size, type, etc.) and cannot perform semantic understanding of file contents, resulting in limited search effectiveness.
Recommendation: Suggest the user enable content awareness to improve search quality. Since existing MetaQuery configurations cannot be directly modified, recommend the user switch to a new bucket and re-enable MetaQuery with content awareness following the Task 2 process.
b. Content awareness IS enabled:
If the user's MetaQuery has content awareness enabled but a specific file still cannot be found, possible reasons include:
File is still being processed: Content awareness requires deep analysis of files (e.g., image recognition, video understanding), which takes longer, especially for video files. Check the Phase field via aliyun ossutil api get-meta-query-status --bucket <bucket-name> --output-format json --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery:
FullScanning: The overall index is still in full scan mode. Wait patiently.
IncrementalScanning: Newly uploaded files are being processed incrementally. Usually wait a few minutes.
Unsupported file format: Some file formats may not be supported by content awareness. In this case, search can only use basic metadata.
Search keywords don't match: The user's search keywords may not semantically match the file content. Suggest the user try adjusting their search keywords to use descriptions closer to the actual file content.
Task 4: Query Data Index Status (aliyun ossutil)
bash
aliyun ossutil api get-meta-query-status --bucket <bucket-name> --output-format json --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
For detailed descriptions of returned fields (State, Phase, MetaQueryMode, etc.), see the GetMetaQueryStatus section in references/related-apis.md.
# Close the data index. (Dangerous operation -- confirm with the user first)
aliyun ossutil api close-meta-query --bucket <bucket-name> --user-agent AlibabaCloud-Agent-Skills/alibabacloud-oss-manage-metaquery
Warning: After closing the data index, all indexed data will be cleared. (Dangerous operation -- confirm with the user first)
Alternative Python Scripts for OSS Operations
When aliyun ossutil is unavailable, you can use Python scripts as alternatives. See the Python SDK Scripts section in references/related-apis.md.