Loading...
Manage AI Models
Enable, configure, and set defaults for your domain
Default AI Model
—
Supporting AI Models
—
Total AI Model Catalog
—
Loading models...
Model Configuration
Optional friendly name that describes this model's specialty or role in your domain (e.g., "Legal Expert", "Creative Writer")
Optional description of what this model is used for in your domain
Sales-oriented description shown in onboarding modals when users select this model. Explain what makes this model special and when to use it.
Custom instructions for this model in your domain. Define how the AI should behave and respond.
This is THE system prompt used for this model in your domain.
📘 Parameter Guide & Best Practices
🌡️ Temperature (0.0–2.0)
Controls randomness in word choice:
• Lower (0.0–0.3): Deterministic, terse, formal. Good for policy text, compliance, code.
• Medium (0.4–0.8): Balanced, natural tone. General-purpose Q&A.
• Higher (0.9–1.3): Creative, varied, chatty. Brainstorming.
• Very high (1.4–2.0): Highly diverse; expect occasional off-track output.
💡 For professional assistants: 0.2–0.5 reads professional without stiffness.
Controls randomness in word choice:
• Lower (0.0–0.3): Deterministic, terse, formal. Good for policy text, compliance, code.
• Medium (0.4–0.8): Balanced, natural tone. General-purpose Q&A.
• Higher (0.9–1.3): Creative, varied, chatty. Brainstorming.
• Very high (1.4–2.0): Highly diverse; expect occasional off-track output.
💡 For professional assistants: 0.2–0.5 reads professional without stiffness.
📏 Max Tokens (positive integer)
Hard cap on output length (tokens = words + word pieces):
• Short replies/alerts: 256–512
• Detailed answers: 800–1200
• Long summaries/drafts: 1500–2000+
⚠️ Smaller = faster & cheaper, but risks truncation. Larger = fuller answers, more cost.
Hard cap on output length (tokens = words + word pieces):
• Short replies/alerts: 256–512
• Detailed answers: 800–1200
• Long summaries/drafts: 1500–2000+
⚠️ Smaller = faster & cheaper, but risks truncation. Larger = fuller answers, more cost.
🎯 Top P (0.0–1.0)
"Nucleus sampling" - samples from smallest set of words with cumulative probability ≥ p:
• Lower (0.1–0.5): Conservative wording (like lower temperature).
• Higher (0.8–1.0): Diverse wording (like higher temperature).
⚠️ Important: Use Temperature OR Top-P, not both. They overlap in effect. When in doubt, leave Top-P blank and tune Temperature only.
"Nucleus sampling" - samples from smallest set of words with cumulative probability ≥ p:
• Lower (0.1–0.5): Conservative wording (like lower temperature).
• Higher (0.8–1.0): Diverse wording (like higher temperature).
⚠️ Important: Use Temperature OR Top-P, not both. They overlap in effect. When in doubt, leave Top-P blank and tune Temperature only.
🎛️ Practical Presets (copyable)
Strict/Compliance: Temp: 0.2, Max: 400, Top-P: blank
General Assistant: Temp: 0.5, Max: 900, Top-P: blank
Creative/Newsletter: Temp: 0.9, Max: 1500, Top-P: blank
💰 Cost & Performance: Grows with output length (Max Tokens) and sometimes with higher creativity.
🔒 Determinism: Set Temperature = 0.0 for most repeatable outputs (slight variance may still occur).
✂️ Truncation: If answers cut off mid-sentence, raise Max Tokens or ask for shorter answers.
🔒 Determinism: Set Temperature = 0.0 for most repeatable outputs (slight variance may still occur).
✂️ Truncation: If answers cut off mid-sentence, raise Max Tokens or ask for shorter answers.
Range: 0.0–2.0. Controls randomness. Lower = deterministic, higher = creative.
Maximum output length. Positive integer. Blank = provider default.
Range: 0.0–1.0. Use Temperature OR Top-P, not both. Leave blank recommended.
📤
Drop files here or click to browse
Supported formats: PDF, TXT, MD, DOCX, JSON, HTML, CSV
⚠️ Maximum 10 files per upload
🧠
Upload Knowledge Node (ZIP)
Must contain: node.yaml (manifest) + NODE.md (instructions)
⚠️ Maximum 50MB per bundle
Shows recent activations and test executions for selected node
No logs to display. Select a node and run a test.
Knowledge Node Graph
Visualize and manage relationships between nodes. Drag nodes to rearrange.
Create Relation:
depends_on
complements
supersedes
AI Suggested
📁 Relationship Manager
Import or export node relationship mappings (JSON or ZIP format).
These define how nodes connect in the Knowledge Graph.
Add Relationship
Node Details
Define tools in JSON format. Example: [{"name":"search","description":"Search the web","parameters":{...}}]
Menu (16px)
Chat Response (36px)
No icon uploaded yet
Upload a square PNG, JPG, or WebP image (max 2MB). Recommended: 512x512px or larger. Will be automatically resized to 16px (menu) and 36px (chat).