• Dashboard
  • Conversations
  • Contacts
    • All Contacts
    • Sources
  • SLA Policies
    • Policies
    • Breaches
  • Agent Bots
  • Automation Rules
  • Knowledge Base
  • Help Center
  • Video Calls
  • Labels
  • Chatwoot
    • Instances
    • Agents
    • Teams
    • Connect
  • Tutorials
  • Settings
  • Request Inspector

Create Knowledge Base

Set up a new knowledge base for AI-powered responses

Basic Information
When active, this knowledge base will be available for AI responses

Embedding Configuration
Important
The embedding provider and model cannot be changed after creation. Choose carefully based on your needs.
Ollama (Local)
nomic-embed-text-v2-moe
Determined by the selected embedding model

Chunking Settings
512
512
48
50
Cancel
What is a Knowledge Base?

A knowledge base is a collection of documents that AI agents can search to provide accurate, context-aware responses. Documents are chunked, embedded, and stored for semantic search.

Embedding Providers
  • Ollama: Free, local embeddings. Requires Ollama running locally.
  • OpenAI: Cloud-based, high quality. Requires API key.
Ollama Models
  • nomic-embed-text-v2-moe: High quality MoE model
  • qwen3-embedding: Large multilingual model
  • embeddinggemma: Lightweight, fast
Chunking Tips
  • Chunk Size: Larger chunks = more context, fewer results
  • Overlap: Helps maintain context across chunk boundaries
  • Recommended: 512 tokens with 50 overlap for most cases
Maya v1.0.2 © 2026 Cloud-Inspire Build: 3/13/2026, 4:40:10 PM