Setup & Installation
openclaw skills install @krisyejh/bailian-knowledge-retrieve
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install bailian-knowledge-retrieve
What This Skill Does
Retrieves vectorized proprietary data from Alibaba Bailian hosted knowledge bases. Returns ranked, relevant document chunks suited for LLM consumption. Uses Bailian's embedding and rerank APIs under the hood.
Eliminates the need to manage your own vector database or embedding pipeline by using Alibaba's hosted infrastructure.
When to use it
- Searching internal company documentation with a chatbot
- Grounding LLM responses in proprietary product manuals
- Querying a private FAQ database for customer support agents
- Retrieving relevant policy documents during an AI workflow
- Pulling context from a vectorized research archive
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: 'What is our refund policy?'
AGENT
- 1Receive user query as input
- 2Run retrieve.py with the query string against the configured knowledge base
- 3Receive top-N ranked document chunks as output
- 4Pass retrieved chunks as context to the LLM
- 5Generate a grounded response based on retrieved content
OUTPUT
Relevant policy document excerpts returned and used to answer the user's question accurately
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
DASHSCOPE_API_KEY environment variableKNOWLEDGEBASE_ID environment variableAlibaba Cloud account with Bailian service enabled