# GenAI Launchpad | Datalumina

## Docs

- [Releases](https://launchpad.datalumina.com/docs/changelog/updates.md): Release notes
- [Agent Node](https://launchpad.datalumina.com/docs/core/agent-node.md): Discover how to integrate Large Language Models into your workflows using the AgentNode class powered by PydanticAI.
- [Agent Streaming Node](https://launchpad.datalumina.com/docs/core/agent-streaming-node.md): Learn how to build streaming LLM responses with the AgentStreamingNode class for real-time token delivery.
- [Base Node](https://launchpad.datalumina.com/docs/core/base-node.md): Learn about the foundational Node class that all other node types inherit from, and how to implement custom processing logic.
- [Concurrent Node](https://launchpad.datalumina.com/docs/core/concurrent-node.md): Learn how to implement concurrent processing with ConcurrentNode to improve performance by running independent operations simultaneously.
- [Types of Nodes](https://launchpad.datalumina.com/docs/core/nodes.md): Explore the four primary node types that serve as building blocks for workflow processing steps, each designed for specific use cases.
- [Overview](https://launchpad.datalumina.com/docs/core/overview.md): Learn about the core package that provides a flexible DAG-based workflow system for processing tasks through interconnected nodes.
- [Router Node](https://launchpad.datalumina.com/docs/core/router-node.md): Implement dynamic workflow routing with BaseRouter and RouterNode classes to create conditional branching based on processing results.
- [Task Context](https://launchpad.datalumina.com/docs/core/task-context.md): Learn how the TaskContext provides stateful data management throughout workflow execution, enabling seamless data sharing between nodes.
- [Workflow Orchestration](https://launchpad.datalumina.com/docs/core/workflow.md): Understand the DAG-based workflow system that manages node execution and data flow through directed processing pipelines.
- [Chat Completion](https://launchpad.datalumina.com/docs/examples/chat-completion.md): Build a chat interface with real-time and direct response modes
- [PGVector RAG](https://launchpad.datalumina.com/docs/examples/pgvector-rag.md): Build Retrieval Augmented Generation workflows using PostgreSQL with pgvector extension
- [SSE Streaming](https://launchpad.datalumina.com/docs/examples/sse-streaming.md): Build real-time streaming chat applications with Server-Sent Events and OpenAI-compatible API
- [Celery Workers](https://launchpad.datalumina.com/docs/framework/celery-workers.md): Implement background task processing with Celery for scalable GenAI event-driven architectures
- [Docker](https://launchpad.datalumina.com/docs/framework/docker.md): Understand the modular Docker architecture for development and production deployments
- [FastAPI](https://launchpad.datalumina.com/docs/framework/fastapi.md): Leverage FastAPI framework for endpoints, authentication, and HTTP communication in GenAI applications
- [Supabase](https://launchpad.datalumina.com/docs/framework/supabase.md): Leverage Supabase as a comprehensive backend-as-a-service platform
- [Installation Guide](https://launchpad.datalumina.com/docs/getting-started/installation.md): Step-by-step installation for GenAI Launchpad
- [System Requirements](https://launchpad.datalumina.com/docs/getting-started/requirements.md): Prerequisites for running GenAI Launchpad
- [End-to-End Testing](https://launchpad.datalumina.com/docs/quickstart/e2e-testing.md): Test the complete workflow with API, database, and background processing
- [Create API Endpoint](https://launchpad.datalumina.com/docs/quickstart/endpoint.md): Build a FastAPI endpoint to receive events and trigger workflows
- [Overview](https://launchpad.datalumina.com/docs/quickstart/overview.md): Build your first GenAI workflow - a customer care automation system
- [Define Your Schema](https://launchpad.datalumina.com/docs/quickstart/schema.md): Create a Pydantic schema to define your data structure
- [Testing Your Workflow](https://launchpad.datalumina.com/docs/quickstart/testing.md): Test workflows locally before deployment
- [Workflow Definition](https://launchpad.datalumina.com/docs/quickstart/workflow-definition.md): Create the workflow structure and register it in the system
- [Workflow Implementation](https://launchpad.datalumina.com/docs/quickstart/workflow-implementation.md): Build the complete customer care workflow with AI-powered nodes
- [Database Migrations](https://launchpad.datalumina.com/docs/tools/alembic.md): Manage database schema changes systematically with Alembic migrations
- [Langfuse Integration](https://launchpad.datalumina.com/docs/tools/langfuse.md): Monitor and trace every step of your GenAI workflows with comprehensive observability
- [Prompt Management](https://launchpad.datalumina.com/docs/tools/prompt-management.md): Create and manage dynamic prompts using Jinja templates for GenAI applications
- [Deploying on a VPS](https://launchpad.datalumina.com/docs/tutorials/deploying-on-vps.md): Step-by-step guide to deploying GenAI Launchpad on a production Linux server
- [Introduction](https://launchpad.datalumina.com/docs/welcome/introduction.md): A production-ready foundation for event-driven AI applications
- [License](https://launchpad.datalumina.com/license.md): License terms and conditions for using the GenAI Launchpad