AI Chat
Conversational AI interface with document context, tool integration, and multiple reasoning modes.
AI Chat is the primary way to interact with Fabric's AI capabilities. It supports real-time streaming, document uploads for context, MCP tool execution, and multiple reasoning depths.
Chat Modes
Fabric offers two chat modes, each suited to different tasks:
Direct Chat
Best for quick conversations and straightforward tasks:
- Real-time streaming responses
- Direct MCP tool execution
- Document upload and RAG context
- Semantic memory integration
- Conversation persistence
Orchestrator Chat
Best for complex, multi-step tasks:
- Durable workflow-based execution
- Multi-agent task coordination
- Human-in-the-loop approval flows
- Task plan visualization and progress tracking
- Step-by-step reasoning with verification
Reasoning Depth
The depth of AI reasoning depends on the model and task type you have configured. Models with reasoning capabilities (such as o1 or DeepSeek R1) provide deeper analysis with step-by-step verification, while fast models (such as GPT-4o-mini or Llama via Groq) optimize for speed.
Configure model preferences per task type in Settings → AI Providers. See AI Providers for details.
Starting a Conversation
Open AI Chat
Click Chat in the left sidebar to open the AI Chat interface.
Choose Your Approach
You can start from:
- Free text — Type your question or task directly
- With documents — Upload files for context before asking
Send Your Message
Type your message and press Enter. The AI streams its response in real-time.
Document Upload
Upload documents to give the AI context about your work. The AI uses RAG (Retrieval-Augmented Generation) to reference your documents when responding.
Supported Formats
| Category | Formats |
|---|---|
| Documents | PDF, DOCX, TXT, MD, HTML, JSON |
| Images | JPEG, PNG, GIF, WEBP, TIFF (OCR extraction) |
Maximum file size: 10 MB per file
How Document Context Works
- Upload — Drag and drop files or click to upload
- Processing — Files are automatically extracted, chunked, and embedded
- Ready — Documents become available for semantic search
- Retrieval — When you send a message, the AI retrieves the most relevant sections from your documents and includes them as context
Document Status
| Status | Description |
|---|---|
| Pending | File uploaded, waiting to be processed |
| Processing | Extraction, chunking, and embedding in progress |
| Ready | Document available for RAG retrieval |
| Failed | Processing encountered an error |
MCP Tool Integration
When MCP servers are configured, the AI can use their tools during conversations.
Tool Suggestions
As you type, the AI suggests relevant MCP tools based on your input:
- Suggestions appear after 5+ characters
- Shows tool name, source server, and description
- Click a suggestion to include it in your message
Tool Execution
During a conversation, the AI may call MCP tools to complete tasks:
- Tool call cards display the tool name, arguments, and results
- Some tools require confirmation before execution
- Results are incorporated into the AI's response
Conversation Management
History
Access past conversations from the sidebar:
- Search conversations by title or content
- Pin important conversations for quick access
- Archive old conversations to keep things tidy
- Conversations are grouped by date
Checkpoints
Create checkpoints to save conversation state:
- Create a checkpoint at any point in the conversation
- Restore to a previous checkpoint to try a different approach
- Delete checkpoints you no longer need
- Track token usage at each checkpoint
Automatic Titles
Fabric automatically generates descriptive titles for your conversations after the first exchange, making them easy to find later.
Token Usage
The chat interface tracks token usage:
- Input tokens — Tokens in your messages and context
- Output tokens — Tokens in AI responses
- Reasoning tokens — Additional tokens used for deep reasoning
- Cached tokens — Tokens served from cache (faster, lower cost)
- Context estimate — How much of the context window is used
Workflow Execution
The AI can suggest and execute workflows during a conversation:
- The AI identifies a relevant workflow for your task
- A confirmation dialog appears with the workflow name and description
- Click Execute to run or Cancel to skip
- Workflow results are incorporated into the conversation
Multi-Tenant Support
AI Chat works in both personal and organization contexts:
- Personal (
/app/chatbot) — Your private conversations - Organization (
/app/{org}/chatbot) — Organization-scoped conversations - Each context has separate conversation history
- AI model preferences are resolved per context (personal or org-level)
- Document uploads are isolated by context