RAG Agent Platform

🤖 Total Agents

0

📚 Knowledge Bases

0

🧠 Available Models

4

🤖 My Agents

✨ Create New Agent

Agent Name * (0/30)

Organization *

Group (optional)

Model *

Instructions *

Greeting message (optional) Shown as the opening message when users start a chat with this agent

📚 Knowledge & Tools

Knowledge Bases

🔧 Tools — real-time data functions the agent can call

📡 Devices & Sensors — select which devices and sensors this agent can read live data from

🔀 Agent Routes

Route queries to specialized agents based on conditions. This agent can delegate work to other agents.

⚙️ Advanced Settings

Temperature (0-1) Controls randomness. Lower (0.1-0.3) = focused, higher (0.7-1.0) = creative

Max Tokens Maximum response length (~4 chars per token)

Top P (0.1-1) Nucleus sampling. Lower (0.1-0.5) = focused, higher (0.9-1.0) = diverse

Top K (0-10) Limits token choices. Lower = predictable, higher = variety

Chunks per Knowledge Base How many text chunks to retrieve from each KB for context (recommended: 3-5)

Retrieval Method How to process queries before searching knowledge bases

Include citations in responses Shows source references and document citations in responses

Strict RAG Mode When enabled, agent ONLY uses knowledge base content. When disabled, can use general knowledge

Allow image upload Lets users attach an image to chat messages — described via a vision model before reaching this agent

📚 Knowledge Bases

📄 Files in -

🗄️ Archived files (0)

Deleted files are no longer searchable. Restore one from its versions, or delete it permanently.

➕ Upload Files

Supported formats: PDF, Word (.docx), Excel (.xlsx), HTML, CSV, Markdown, text. Up to 5 GB per file.
Uploading a file with an existing name adds a new version. Files are indexed in the background.

⚙️ Chunking

Chunk size (characters)

Chunk overlap (characters)

Applies to every file in this knowledge base. Saving a change re-indexes all files.

🔧 My Tools

✨ Create New Tool

Tool Name * Alphanumeric and underscores only, used in LLM tool calls

Description * Clear description helps the LLM decide when to use this tool

Tool Enabled Only enabled tools are available to agents

📝 JavaScript Code

Write JavaScript code that will be executed when the tool is called. Access arguments via args object. Return the result. Available: axios for HTTP requests, console.log for debugging.

📦 Dependencies (Optional)

List npm packages needed by this tool (one per line). They will be installed automatically. Example: aws-sdk, node-fetch, cheerio

⚙️ Parameters Schema

Define parameters in JSON Schema format. This tells the LLM what arguments the tool expects.

Available Models

Language models via DigitalOcean AI Inference • Embedding models via OpenAI, DigitalOcean AI, or local HuggingFace

🤖 RAG Agent Platform

🔒 Sign In

🤖 My Agents

Agent Details

✨ Create New Agent

📚 Knowledge Bases

📄 Files in -

➕ Upload Files

⚙️ Chunking

🔧 My Tools

Tool Details

✨ Create New Tool

🧪 Test Tool

Result:

Available Models