ADBPG Knowledge Base Management

Build enterprise knowledge bases in three steps: Create Knowledge Base → Upload Documents → Search & Q&A

The system automatically handles document parsing, chunking, vectorization, and index building. Users only need to focus on business logic.

Architecture: ADBPG Instance + Namespace + DocumentCollection + Vector Index + LLM Service

Core Concepts

• Knowledge Base: Container for documents, automatically manages vector indexes (corresponds to DocumentCollection in API)
• Document: Files uploaded to the knowledge base, supports PDF/Word/Markdown/HTML/JSON/CSV/images, etc.
• Q&A: Intelligent conversation based on knowledge base + large language model

Environment Setup

Pre-check: Aliyun CLI >= 3.3.1 required
Run aliyun version to verify >= 3.3.1. If not installed or version too low,
see [references/cli-installation-guide.md](references/cli-installation-guide.md) for installation instructions.
Then [MUST] run aliyun configure set --auto-plugin-install true to enable automatic plugin installation.

Pre-check: Alibaba Cloud Credentials Required

Security Rules:
- NEVER read, echo, or print credential material (including environment-based secrets)
- NEVER ask the user to paste long-lived secrets directly in the conversation or command line
- NEVER use aliyun configure set with literal credential values
- ONLY use aliyun configure list to check credential status

```bash
aliyun configure list
```
Check the output for a valid profile (AK, STS, or OAuth identity).

If no valid profile exists, STOP here.
1. Obtain credentials from Alibaba Cloud Console
2. Configure credentials outside of this session (via aliyun configure in terminal or environment variables in shell profile)
3. Return and re-run after aliyun configure list shows a valid profile

Verify CLI Credentials

aliyun gpdb describe-regions --user-agent AlibabaCloud-Agent-Skills

Script dependencies (Python)

[scripts/uploaddocumentlocal.py](scripts/uploaddocumentlocal.py) uses the Alibaba Cloud Python SDK. Declare dependencies in [requirements.txt](requirements.txt). Install before running the script:

pip install -r requirements.txt

Requires Python 3.7+ (same baseline as Alibaba Cloud SDK for Python).

RAM Permissions

[MUST] RAM Permission Pre-check: Before executing operations, verify current user has required permissions.
Use ram-permission-diagnose skill to check permissions, then compare against [references/ram-policies.md](references/ram-policies.md).
If any permission is missing, abort and prompt user.

Parameter Confirmation

IMPORTANT: Parameter Confirmation — Before executing any command or API call,
ALL user-customizable parameters (e.g., RegionId, instance names, CIDR blocks,
passwords, domain names, resource specifications, etc.) MUST be confirmed with the
user. Do NOT assume or use default values without explicit user approval.

Note: If the knowledge base is created in a custom namespace, all subsequent operations must specify the same namespace parameter.

For interaction guidelines, smart defaults, and best practices, see [references/interaction-guidelines.md](references/interaction-guidelines.md).

Documentation placeholders: CLI examples use strings like <manager-account-password> and <namespace-password>. Replace them with real values from the user; never commit or log real passwords in docs, tickets, or chat.

Timeout Configuration

Timeout Rules: All operations must complete within reasonable time limits.

- Standard operations: ≤10 seconds (create/list/query)
- Upload document async: No timeout limit (async job, poll every 5-10s)

CLI Timeout Settings:

# Add --ConnectTimeout and --ReadTimeout to all commands
aliyun gpdb create-document-collection \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --manager-account admin_user \
  --manager-account-password '<manager-account-password>' \
  --namespace ns_my_knowledge_base \
  --collection my_knowledge_base \
  --embedding-model text-embedding-v4 \
  --dimension 1024 \
  --user-agent AlibabaCloud-Agent-Skills \
  --ConnectTimeout 10 \
  --ReadTimeout 10

Python SDK (default credential chain + timeouts + User-Agent):

Use CredentialClient() with no arguments so the SDK resolves credentials via the default chain (same sources as the CLI). Do not parse credential files or pass raw keys in skill code. Set user_agent and HTTP timeouts on Config (milliseconds).

from alibabacloud_credentials.client import Client as CredentialClient
from alibabacloud_gpdb20160503.client import Client
from alibabacloud_tea_openapi.models import Config

client = Client(Config(
    credential=CredentialClient(),
    region_id='cn-hangzhou',
    endpoint='gpdb.aliyuncs.com',
    connect_timeout=10000,
    read_timeout=10000,
    user_agent='AlibabaCloud-Agent-Skills',
))

Core Workflow

1. Knowledge Base Management

Create Knowledge Base

Pre-checks (run in order; not silent idempotency):

• Duplicate names: If a create step is run again when the resource already exists, the API returns a clear error (e.g. conflict / already exists). Do not create duplicate resources; interpret already-exists-style errors as “this step is satisfied” only when the response clearly indicates the resource is present, then continue the workflow.
• Retries / ClientToken: For network-level retries (e.g. timeout), use ClientToken when the API or aliyun gpdb exposes it for that subcommand—check aliyun gpdb <subcommand> --help. The examples below omit it when the plugin does not list it globally.

# 1. Initialize vector database
aliyun gpdb init-vector-database \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --manager-account admin_user \
  --manager-account-password '<manager-account-password>' \
  --user-agent AlibabaCloud-Agent-Skills

# 2. Create namespace (naming rule: ns_{collection}, public is forbidden)
aliyun gpdb create-namespace \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --manager-account admin_user \
  --manager-account-password '<manager-account-password>' \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --user-agent AlibabaCloud-Agent-Skills

Important: CreateNamespace MUST be executed before CreateDocumentCollection

Create knowledge base:

# 3. Create knowledge base (in the previously created namespace)
aliyun gpdb create-document-collection \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --manager-account admin_user \
  --manager-account-password '<manager-account-password>' \
  --namespace ns_my_knowledge_base \
  --collection my_knowledge_base \
  --embedding-model text-embedding-v4 \
  --dimension 1024 \
  --user-agent AlibabaCloud-Agent-Skills

List Knowledge Bases

aliyun gpdb list-document-collections \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --user-agent AlibabaCloud-Agent-Skills

List Namespaces

aliyun gpdb list-namespaces \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --manager-account admin_user \
  --manager-account-password '<manager-account-password>' \
  --user-agent AlibabaCloud-Agent-Skills

2. Document Management

Upload Document (Public URL)

aliyun gpdb upload-document-async \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --collection my_knowledge_base \
  --file-name "user_manual.pdf" \
  --file-url "https://example.com/user_manual.pdf" \
  --document-loader-name ADBPGLoader \
  --chunk-size 500 \
  --chunk-overlap 50 \
  --user-agent AlibabaCloud-Agent-Skills

Upload Document (Local File - SDK)

Local files use Python SDK uploaddocumentasyncadvance. Do not paste multi-line Python into the skill; use the packaged script only (default credential chain, useragent, Config timeouts, and RuntimeOptions timeouts — see scripts/uploaddocumentlocal.py).

python3 scripts/upload_document_local.py \
  --region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --collection my_knowledge_base \
  --file /path/to/local/file.pdf

See [scripts/uploaddocumentlocal.py](scripts/uploaddocumentlocal.py).

Poll Upload Progress

aliyun gpdb get-upload-document-job \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --collection my_knowledge_base \
  --job-id "job-xxxxx" \
  --user-agent AlibabaCloud-Agent-Skills

List Documents

aliyun gpdb list-documents \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --collection my_knowledge_base \
  --user-agent AlibabaCloud-Agent-Skills

3. Search & Q&A

Search Knowledge Base

aliyun gpdb query-content \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --namespace ns_my_knowledge_base \
  --namespace-password '<namespace-password>' \
  --collection my_knowledge_base \
  --content "How to configure database parameters?" \
  --topk 10 \
  --rerank-factor 5 \
  --user-agent AlibabaCloud-Agent-Skills

Knowledge Base Q&A

aliyun gpdb chat-with-knowledge-base \
  --biz-region-id cn-hangzhou \
  --db-instance-id gp-xxxxx \
  --model-params '{"Model":"qwen-max","Messages":[{"Role":"user","Content":"User question"}]}' \
  --knowledge-params '{"SourceCollection":[{"Collection":"my_knowledge_base","Namespace":"ns_my_knowledge_base","NamespacePassword":"<namespace-password>","QueryParams":{"TopK":10}}]}' \
  --user-agent AlibabaCloud-Agent-Skills

Reference Links