serviette

# serviette

> **Looking for llm-app templates?** All templates, cookbooks and examples
> are still available in full in the
> [Pathway repository under `examples/llm-app`](https://github.com/pathwaycom/pathway/tree/main/examples/llm-app).

<p align="center">
  <a href="https://pypi.org/project/serviette/"><img src="https://img.shields.io/pypi/v/serviette?logo=pypi&logoColor=white" alt="PyPI version"></a>
  <a href="https://pypi.org/project/serviette/"><img src="https://img.shields.io/pypi/pyversions/serviette?logo=python&logoColor=white" alt="Python versions"></a>
  <a href="https://github.com/pathwaycom/serviette/blob/main/LICENSE"><img src="https://img.shields.io/github/license/pathwaycom/serviette" alt="License: MIT"></a>
  <a href="https://github.com/pathwaycom/serviette/actions/workflows/ci.yml"><img src="https://github.com/pathwaycom/serviette/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
</p>

**A no-code, always up-to-date RAG server for any vector database — built on
the [Pathway Live Data Framework](https://github.com/pathwaycom/pathway).**

Point serviette at a folder of documents, pick a vector database and an
embedder in one YAML file, and run two commands: you get a chat and a REST API
that answer from those documents and cite their sources. From then on, any
change to the documents — an edit, a new file, a deletion — is reflected in
the answers within seconds.

serviette runs on Pathway, which needs a **free license key** — one click at
<https://pathway.com/framework/get-license> (GitHub or LinkedIn sign-in). Every
command below expects it in `PATHWAY_LICENSE_KEY`.

Try it in four commands:

```bash
pip install serviette
export PATHWAY_LICENSE_KEY=...        # free: https://pathway.com/framework/get-license
export OPENAI_API_KEY=sk-...
serviette demo --embedder openai      # → chat at http://localhost:8989
```

**Use pip 23.1 or newer** (`python -m pip install -U pip` first): older pip lacks
the resolver improvements this dependency tree needs and can take hours.

This indexes a [small bundled corpus](https://github.com/pathwaycom/serviette/tree/main/serviette/demo/corpus) (a fictional
coffee-machine company) into `./serviette-demo/docs` and opens a chat over
it. Edit or drop files into that folder while it runs — the answers
follow within seconds.

<p align="center">
  <img src="https://raw.githubusercontent.com/pathwaycom/serviette/main/docs/assets/demo.gif" alt="serviette demo: the terminal output up to the Ready line, the chat answering a question, a one-line edit of a document in a second terminal, and the same question answered with the new value" width="100%">
</p>
<p align="center"><em>One command to a live RAG stack — then edit a document and watch the answer change.</em></p>

## Who is it for

**What you get.** A question-answering assistant over your organisation's
documents, with sources cited and answers that follow the documents: an edit,
a new file or a deletion is reflected within seconds, with no re-upload or