Skip to content
  1. Home
  2. AI tools
  3. serviette

serviette

No-code RAG server that keeps answers in sync with a document folder

What it is

A command-line RAG server built on the Pathway framework. You point it at a folder, choose a vector database and embedder in one YAML file, and get a chat UI and REST API that answer with citations and pick up file edits, additions and deletions within seconds. The repo was formerly Pathway's llm-app templates, which now live in the main Pathway repo.

Good for

  • Stand up a cited Q&A API over a folder
  • Keep a RAG index fresh as files change
  • Compare vector databases behind one config

Install or run

pip install serviette

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Python with pip 23.1+, a free Pathway licence key and an embedder/LLM key such as OpenAI

Worth knowingRequires registering for a Pathway licence key even though it is free; the star count was earned under the earlier llm-app project.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • MarkItDown

    microsoft/markitdown

    Lightweight Python utility that converts files to Markdown for LLMs

    ToolGitHub stars: 195k
  • RAGFlow

    infiniflow/ragflow

    Self-hosted RAG engine with document parsing and agent templates

    ToolGitHub stars: 94k
  • Docling

    docling-project/docling

    Parse PDFs, Office files and more into structured data for LLMs

    ToolGitHub stars: 71k
  • LightRAG

    HKUDS/LightRAG

    Graph-based RAG library and server with pluggable storage backends

    ToolGitHub stars: 41k