Metadata-Version: 2.4
Name: videosdk-conversational-graph
Version: 1.0.1
Summary: Conversational graph package
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Dynamic: requires-python

# Conversational Graph

Build deterministic, multi-turn voice and chat AI agents as directed graphs : where you control the flow and the LLM handles natural conversation.


## Installation

```bash
pip install videosdk-conversational-graph
```

## Features

| Capability | How It Works |
|------------|-------------|
| **Predictable flows** | Conversations follow the exact path you define. No hallucinated detours. |
| **Structured data collection** | Extract and validate user data with Pydantic models : types, constraints, custom validators. |
| **Conditional branching** | Route to different paths based on collected data (e.g., credit score -> approve/reject/review). |
| **Human-in-the-loop** | Pause the conversation, wait for external input (payment callback, human review), then resume. |
| **Checkpointing** | Save conversation state after every step. Resume interrupted calls. Time-travel to any past point. |
| **Parallel tool execution** | Run multiple nodes or tool calls concurrently with fan-out/fan-in transitions. |
| **Provider agnostic** | Works with any STT, LLM, TTS via the VideoSDK pipeline. |
