A community-driven skill for building Retrieval-Augmented Generation (RAG) pipelines using DigitalOcean Gradient and Spaces storage.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gradient-knowledge-base
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gradient-knowledge-base using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Gradient Knowledge Base & RAG?
The Gradient Knowledge Base skill empowers developers to build sophisticated Retrieval-Augmented Generation (RAG) pipelines on DigitalOcean infrastructure. As part of the Openclaw Skills ecosystem, this tool simplifies document management by connecting DO Spaces with managed OpenSearch indices. It allows AI agents to perform semantic and hybrid searches, turning static files into actionable intelligence.
By using Openclaw Skills like this one, you can ensure your AI has the most relevant context for every query. This unofficial community skill provides a bridge between your raw data stored in S3-compatible buckets and the Gradient AI Platform's inference capabilities, making it an essential component for developers building knowledgeable and reliable AI agents.
Gradient Knowledge Base & RAG Use Cases
- Creating private RAG pipelines using DigitalOcean's managed infrastructure and Openclaw Skills.
- Automating the indexing of technical documentation, research papers, or financial filings.
- Enhancing AI agent responses with context-aware data retrieved via semantic search.
- Performing hybrid search to find exact keywords like ticker symbols alongside conceptual meanings.
How Gradient Knowledge Base & RAG Works
- Documents are uploaded to DigitalOcean Spaces via S3-compatible scripts.
- A Knowledge Base is created or selected using the management tools within the Openclaw Skills framework.
- The Spaces bucket is linked as a data source, which triggers indexing into a managed OpenSearch instance.
- Users execute queries that can be tuned between lexical (keyword) and semantic (meaning) search using the alpha parameter.
- For full RAG workflows, the skill retrieves relevant chunks and sends them to an LLM to synthesize a final answer with citations.
Gradient Knowledge Base & RAG Setup
To get started with this skill, you must configure your DigitalOcean and Gradient credentials:
# Core Authentication
export DO_API_TOKEN="your_digitalocean_api_token"
export GRADIENT_API_KEY="your_gradient_ai_key"
export DO_SPACES_ACCESS_KEY="your_spaces_access_key"
export DO_SPACES_SECRET_KEY="your_spaces_secret_key"
# Optional Configuration
export DO_SPACES_BUCKET="your-default-bucket"
export GRADIENT_KB_UUID="your-kb-uuid"
Ensure you have Python 3 installed and the required libraries: pip install requests boto3.
Gradient Knowledge Base & RAG Data Schema & Taxonomy
The skill manages data across storage and indexing layers as follows:
| Component | Type | Description |
|---|---|---|
| Source Files | PDF, MD, TXT | Private documents stored in DigitalOcean Spaces |
| Knowledge Base | UUID | A managed container for indexed document vectors |
| Data Source | UUID | The connection between a specific Spaces prefix and a Knowledge Base |
| Chunks | Vector | Fragmented document parts used for semantic retrieval |
Gradient Knowledge Base & RAG Advanced Features
- Hybrid Search Tuning: Use the alpha parameter (0.0 to 1.0) to balance between keyword matching and semantic meaning.
- RAG-Enhanced Queries: Automatically pipeline search results into LLMs like GPT-4 or OSS models for synthesized answers.
- Multi-Region Support: Manage Knowledge Bases across different DigitalOcean regions such as NYC3.
- Auto-Indexing: Leverage DigitalOcean's native auto-detection to update your index whenever files change in Spaces.
- JSON Output: All tools support machine-readable output for integration into larger Openclaw Skills automation workflows.
SKILL.md
Loading
Related Openclaw Skills
Gradient Inference for DigitalOcean
Integrate DigitalOcean's Gradient Serverless Inference into your AI agent workflows for high-performance LLM chat and image generation.
River Memory
A local semantic memory system utilizing Ollama to provide vector-based search and storage capabilities for AI agents.
Image Generator Skill
A local image generation workflow supporting Stable Diffusion 1.5 and SDXL models integrated with non-blocking subagent execution.
Exa Search & Research MCP
A powerful neural search integration that enables AI agents to perform advanced web crawling and deep research using the Exa protocol.
Workshop to Miro Diagram
Converts physical workshop artifacts like photos and notes into professionally structured, editable Miro boards using intelligent frames and stickies.
MolTravel
A unified travel intelligence skill for AI agents offering real-time flights, visa requirements, and destination activities.
Featured*
