pathwaycom/llm-app

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

What it solves

This project provides a set of ready-to-deploy AI application templates designed for high-accuracy RAG (Retrieval-Augmented Generation) and enterprise search at scale. It solves the problem of maintaining complex infrastructure dependencies—such as separate vector databases, caches, and API frameworks—by integrating these components into a unified pipeline.

How it works

The pipelines are built on the Pathway Live Data Framework, which handles real-time synchronization with data sources like Google Drive, S3, Kafka, and PostgreSQL. The system uses built-in in-memory indexing (via usearch for vector search and Tantivy for full-text search) to enable hybrid search capabilities. These applications can be deployed as Docker containers and expose an HTTP API for frontend connectivity, with some templates including a Streamlit UI for testing.

Who it’s for

Developers and enterprises looking to quickly deploy production-ready RAG applications that stay synchronized with live data sources and can scale to millions of pages of documents.

Highlights

  • Live Data Sync: Automatically syncs additions, deletions, and updates from various file systems and cloud storage.
  • Canned Templates: Includes specialized pipelines for multimodal RAG (GPT-4o), video RAG (TwelveLabs), and unstructured-to-SQL conversion.
  • Infrastructure-less: Eliminates the need for external vector databases or Redis caches by using built-in in-memory indexing.
  • LlamaIndex/LangChain Integration: Can be used as a retriever backend for existing LLM frameworks.
  • Adaptive RAG: Features a technique to reduce token costs by up to 4x while maintaining accuracy.

Related

  • Project
    pathwaycom/pathway

    Pathway is a Python‑first, Rust‑backed framework for building batch‑or‑stream data pipelines. It offers connectors to many sources, stateful operators, persistence, and a dedicated LLM toolkit (wrappers, parsers, vector index) that makes real‑time RAG and other LLM applications easy to write and deploy via Docker or Kubernetes.

  • Project
    swirlai/swirl-search

    A federated AI search and RAG platform that queries data sources live, eliminating the need for vector databases and ETL pipelines while keeping data in place.

  • Project
    ray-project/llm-applications

    A comprehensive guide and implementation for building, scaling, and productionizing RAG-based LLM applications using the Ray framework.

  • Project
    shaiwz/data-platform-open

    A zero-code, visual drag-and-drop big data integration platform that uses AI to help users build data pipelines and query templates without writing code.

  • Project
    infiniflow/ragflow

    An open-source RAG engine that combines deep document understanding and agentic capabilities to create a high-fidelity context layer for LLMs using complex unstructured data.