AI Providers

AIProvider

Bases: ABC

AI model provider for generating responses.

name property

name

Provider name (e.g. 'anthropic', 'openai').

supports_vision property

supports_vision

Whether this provider can process images.

model_name abstractmethod property

model_name

Model identifier (e.g. 'claude-sonnet-4-20250514', 'gpt-4o').

generate abstractmethod async

generate(context)

Generate an AI response from the given context.

Parameters:

Name	Type	Description	Default
context	AIContext	Conversation context including messages, system prompt, temperature, and target channel capabilities.	required

Returns:

Type	Description
AIResponse	The AI response with content, usage stats, and optional
AIResponse	tasks/observations.

close async

close()

Release resources. Override in subclasses that hold connections.

AIContext

Bases: BaseModel

Context passed to AI provider for generation.

AIMessage

Bases: BaseModel

A message in the AI conversation context.

AITextPart

Bases: BaseModel

Text part of a multimodal message.

AIImagePart

Bases: BaseModel

Image part of a multimodal message.

AITool

Bases: BaseModel

Tool definition for function calling.

AIToolCall

Bases: BaseModel

A tool call from the AI response.

AIResponse

Bases: BaseModel

Response from an AI provider.

MockAIProvider

MockAIProvider(responses=None, *, vision=False)

Bases: AIProvider

Round-robin response provider for tests.

Per-Room AI Configuration

AI channel settings can be overridden per-room using binding metadata:

# Default AI channel
ai = AIChannel("ai", provider=anthropic, system_prompt="Default assistant")
kit.register_channel(ai)

# Override per room
kit.attach_channel(room_id, "ai", metadata={
    "system_prompt": "You are a customer support agent for Acme Corp.",
    "temperature": 0.3,  # More deterministic
    "max_tokens": 2048,
})

Silent Observer Pattern (Meeting Notes)

# Attach AI as note-taker
kit.attach_channel(meeting_room_id, "ai", metadata={
    "system_prompt": """You are a meeting note-taker.
    Listen to the conversation silently.
    When someone says 'meeting ended', compile and send a summary.""",
})

# Mute so AI listens but doesn't respond
await kit.mute(meeting_room_id, "ai")

# Later, unmute to let AI send summary
await kit.unmute(meeting_room_id, "ai")

Tools/Function Calling

Tools can be passed via binding metadata for function calling:

kit.attach_channel(room_id, "ai", metadata={
    "tools": [
        {
            "name": "search_knowledge_base",
            "description": "Search the company knowledge base",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string"}
                },
                "required": ["query"]
            }
        }
    ]
})

Tool calls are returned in AIResponse.tool_calls:

response = await provider.generate(context)
for tool_call in response.tool_calls:
    print(f"Tool: {tool_call.name}, Args: {tool_call.arguments}")

Gemini Provider

GeminiAIProvider

GeminiAIProvider(config)

Bases: AIProvider

AI provider using the Google Gemini API.

supports_vision property

supports_vision

All Gemini models support vision.

GeminiConfig

Bases: BaseModel

Google Gemini AI provider configuration.

Usage

from roomkit import GeminiAIProvider, GeminiConfig

config = GeminiConfig(api_key="your-api-key")
provider = GeminiAIProvider(config)

# Use with AIChannel
ai_channel = AIChannel("ai", provider=provider)

Install with: pip install roomkit[gemini]