for developers

Quick Start

The Pathway AI Pipelines provide a ready-to-use setup for creating real-time, AI-driven applications. With YAML-configured templates, it's easy to customize or create your own processing pipelines for use cases like document indexing, real-time knowledge mining, and alerting.

This quick start guide will help you set up and run Pathway's AI Pipelines, a powerful framework for building real-time, AI-driven applications using large language models (LLMs). Whether you’re developing a document indexing solution, a knowledge mining system, or a query-response interface, this guide will get you started quickly.

Prerequisites

To get started, you'll need:

  • Git to clone the repository and manage updates
  • LLM API Key (e.g., OpenAI or Hugging Face) for embedding and querying models

Running Options

  1. Docker (recommended) will install all dependencies automatically
  2. Python 3.8+ with Pathway if you prefer a local setup.

Note: if you are using Pathway locally, you will need to install Pathway LLM xpack:

pip install pathway[all]

Optional: Install Streamlit for UI and pip for dependency management (if not using Docker).

Clone the Repository

First, you need to download the repository.

git clone https://github.com/pathwaycom/llm-app.git

Selecting Your Template

Pathway AI Pipelines provide several ready-to-go templates for common use cases. Whether you need a real-time alerting system, document indexing, or context-based Q&A, you’ll find templates for each. If none match your needs exactly, the framework provides all the necessary tools to create your own pipeline.

See the templates.

Then you need to go the repository of the chosen template, let's take the demo-question-answering as an example.

cd llm-app/examples/pipelines/demo-question-answering

Configuring and Running Pathway AI Pipelines

Most of the templates can be configured using a YAML file. You can learn how to configure them by reading the dedicated tutorial.

You can run Pathway AI Pipelines either locally or using Docker. With Docker, setup is automated, handling all required dependencies. For a local setup, you’ll install dependencies manually using Python and Pathway. For detailed configuration and usage steps, refer to the README and articles included with each template.