local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities.
Why use this skill?
Enhance your OpenClaw agent with local RAG-powered web search. Perform intelligent, semantic-ranked research across Google, DuckDuckGo, and more without external APIs.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/nkapila6/local-rag-searchWhat This Skill Does
The local-rag-search skill integrates the mcp-local-rag server into OpenClaw, allowing for powerful web research capabilities without the need for external API keys. By leveraging semantic similarity ranking, the agent can sift through search results from various engines—including DuckDuckGo, Google, and others—to provide highly relevant, context-aware answers. Unlike basic search tools, this skill uses RAG (Retrieval-Augmented Generation) patterns to prioritize the most pertinent data, ensuring that the information surfaced is accurate and grounded in the source material.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/nkapila6/local-rag-search Once installed, ensure your MCP server configuration is correctly pointed to the local-rag-search executable to enable communication between the agent and the search engine backends.
Use Cases
This skill is ideal for tasks requiring synthesis of information. Use it for:
- Technical Research: Digging into specific programming documentation or library best practices.
- Market Analysis: Gathering current information across multiple sources for a broader perspective.
- General Inquiry: Performing quick, privacy-focused searches without tracking.
- Deep Investigation: When you need to synthesize information from various search engines like Google, Bing, and Wikipedia to form a comprehensive answer.
Example Prompts
- "Find the latest 2024 best practices for React state management and summarize them for a production app."
- "Research the current status of the fusion energy industry; use multiple sources to provide a balanced overview of recent breakthroughs."
- "How do I optimize a Docker multi-stage build? Please search Google for technical guides and return the top 5 most relevant steps."
Tips & Limitations
- Be Specific: Rather than broad keywords, use natural language phrases or questions. The quality of your results is directly proportional to the clarity of your query.
- Tool Selection: Use
rag_search_ddgsfor day-to-day general questions to maintain privacy. Usedeep_researchwhen you are tackling complex topics that require cross-referencing multiple viewpoints. - Limitations: Since this runs locally via MCP, ensure your internet connection is stable. The speed of the search is dependent on the availability of the configured search backends. Note that while this provides deep insights, it is bound by the index limits of the search engines queried.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-nkapila6-local-rag-search": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access