LLM App

Pathway offers cloud templates for RAG, AI pipelines, and enterprise search that stay synchronized with connected data sources.

github.com/pathwaycom/llm-app
LLM App homepage screenshot

About LLM App

LLM App is an open-source repository of ready-to-run application templates for retrieval-augmented generation (RAG), AI pipelines, and enterprise search. The templates are built on the Pathway Live Data Framework. They connect to data sources such as a file system, Google Drive, SharePoint, S3, Kafka, PostgreSQL, and real-time data APIs, and they keep indexed content in sync as data is added, changed, or deleted. The source states that the templates can be tested on a local machine and deployed on cloud platforms (GCP, AWS, Azure, Render) or on-premises.

The templates include built-in indexing for vector, hybrid, and full-text search. The source says these run in memory with cache and need no separate infrastructure setup. The templates run as Docker containers and expose an HTTP API. Some include an optional Streamlit user interface. The source says the templates scale to millions of pages of documents. Several templates depend on external model services, such as GPT models, GPT-4o, or TwelveLabs. The Private RAG template is the one described as fully local, using Mistral and Ollama.

Key features

  • Live sync of added, updated, and deleted records from connected data sources
  • Built-in vector, hybrid, and full-text search indexing kept in memory
  • Question-answering RAG template for PDF and DOCX files from connected sources
  • Multimodal RAG template using GPT-4o to index charts and tables in PDFs
  • Unstructured-to-SQL pipeline that answers natural language questions via SQL
  • Fully local Private RAG template using Mistral and Ollama
Best for: Developers and engineering teams who want to build RAG or enterprise search applications over data sources that change over time.
Good for
  • Open source, with the repository published under a license file
  • Templates can be run locally and deployed on cloud or on-premises infrastructure
  • Source states the templates need no separate infrastructure setup for indexing
Watch out for
  • Several templates depend on external model services such as GPT models or TwelveLabs
  • The optional Streamlit UI is included only in some templates

LLM App at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

LLM App alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Infrastructure & MLOps

Well-known listings from the same topic.

All 341

LLM App FAQ

Can the templates be tested on a local machine?
Yes. The source states that the templates can be tested on your own machine before deployment.
Where can the applications be deployed?
The source lists GCP, AWS, Azure, and Render as cloud options, as well as on-premises deployment.
How do the applications expose their interface?
The apps can run as Docker containers and expose an HTTP API to connect a frontend. Some templates also include an optional Streamlit UI that connects to this API.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing