Neura Market
Llm App logo

Llm App

Free

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.

FreeFree tier
Type
Open Source
Company
Pathway
Visit Website GitHub (59.6k stars)

About Llm App

Pathway Live Data Framework Templates is a collection of ready-to-deploy ETL and RAG pipelines built on the Pathway Live Data Framework. These YAML and Python templates enable developers and non-developers to quickly build and deploy AI applications that process live data from sources like SharePoint, Google Drive, S3, Kafka, PostgreSQL, and over 300 other connectors. The templates cover use cases such as high-accuracy RAG question-answering, private RAG with local models, multimodal document analysis, real-time document indexing, slides search, and financial report structuring. The framework offers a true streaming data processing engine in Rust, incremental stream operations, REST API endpoints, and support for Docker deployment. It is available under a BSL 1.1 license with free Community and Scale tiers, and a paid Enterprise tier for large-scale deployments.

Key Features

Prebuilt YAML and Python templates for RAG and ETL pipelines
Real-time document indexing and vector store service
Support for multimodal RAG (PDFs, slides, images) with GPT-4o
High-accuracy RAG with Adaptive RAG technique (up to 4x token cost reduction)
Private RAG with local models (Mistral, Ollama)
Live sync with 300+ data sources (SharePoint, Google Drive, S3, Kafka, PostgreSQL)
True streaming data processing engine in Rust
REST API endpoints for query/answer with sub-millisecond latency
Docker-friendly deployment
Scalable from single node to multi-node enterprise clusters

Pros & Cons

Pros
  • Open source under BSL 1.1 with free Community and Scale tiers
  • Easy to deploy with Docker and prebuilt templates
  • Automatically syncs with live data sources without manual re-indexing
  • Supports both cloud and on-premise deployment
  • High-performance streaming engine written in Rust
  • Covers a wide variety of use cases from simple RAG to enterprise ETL
  • Includes connectors for over 300 data sources
Cons
  • Free tiers have RAM limits (8 GB Community, 16 GB Scale) which may be restrictive
  • BSL 1.1 license includes limitations for production use (not fully open source)
  • Requires technical knowledge to customize templates beyond defaults
  • Primarily designed for developers with less focus on no-code usage

Best For

Building question-answering RAG pipelines on live documentsCreating a vector store that automatically updates when source files changeQuerying financial reports with a live document structuring pipelineSearching through slide decks with multi-modal indexingImplementing adaptive RAG to reduce token costs while maintaining accuracyDeploying fully private RAG applications with local LLMsETL pipelines for Kafka, log monitoring, social media sentiment analysisReal-time GPS data analytics and IoT fraud detection