Welcome to PlanAI

An innovative system designed for complex task automation through a sophisticated graph-based architecture. PlanAI integrates traditional computations and cutting-edge AI technologies to enable versatile and efficient workflow management.

Get Started

Key Features

Graph-Based Architecture

Construct dynamic workflows comprising interconnected TaskWorkers for highly customizable automation.

Hybrid TaskWorkers

Combine conventional computations (e.g., API calls) with powerful LLM-driven operations, leveraging Retrieval-Augmented Generation (RAG) capabilities.

Type Safety with Pydantic

Ensure data integrity and type consistency across workflows with Pydantic-validated input and output.

Intelligent Data Routing

Utilize type-aware routing to efficiently manage data flow between nodes, adapting to multiple downstream consumers.

Input Provenance Tracking

Trace the lineage and origin of each Task as it flows through the workflow, enabling detailed analysis and debugging of complex processes.

Automatic Prompt Optimization

Improve LLMTaskWorker prompts automatically using AI-driven optimization, enhancing performance with minimal manual intervention.

Real-World Example: Textbook Q&A Generation

PlanAI has been used to create a sophisticated system for generating high-quality question and answer pairs from textbook content. This example demonstrates PlanAI's capability to manage complex, multi-step workflows involving AI-powered text processing and content generation.

Key Components:

  • Text cleaning and formatting
  • Relevance filtering
  • Question generation and evaluation
  • Answer generation and selection
  • Output handling and storage

Monitoring Dashboard:

PlanAI Dashboard
View Full Example

Getting Started

Installation

You can install PlanAI using pip:

pip install planai

Basic Usage

Here's a simple example of how to use PlanAI:


from planai import Graph, TaskWorker, LLMTaskWorker, llm_from_config

# Define custom TaskWorkers
class CustomDataProcessor(TaskWorker):
    output_types = [ProcessedData]

    def consume_work(self, task: RawData):
        processed_data = self.process(task.data)
        self.publish_work(ProcessedData(data=processed_data))

# Define an LLM-powered task
class AIAnalyzer(LLMTaskWorker):
    prompt = "Analyze the provided data and derive insights"
    output_types = [AnalysisResult]

    def consume_work(self, task: ProcessedData):
        super().consume_work(task)

# Create and run the workflow
graph = Graph(name="Data Analysis Workflow")
data_processor = CustomDataProcessor()
ai_analyzer = AIAnalyzer(
    llm=llm_from_config(provider="openai", model_name="gpt-4o")
    )

graph.add_workers(data_processor, ai_analyzer)
graph.set_dependency(data_processor, ai_analyzer)

initial_data = RawData(data="Some raw data")
graph.run(initial_tasks=[(data_processor, initial_data)])

For more detailed examples and advanced usage, please refer to our documentation.

Ready to Transform Your Workflow?

Join the growing community of PlanAI users and take your productivity to the next level.

Documentation GitHub