LLM App

> **Looking for llm-app templates?** All templates, cookbooks and examples
> are still available in full in the
> Pathway repository under examples/llm-app.
**A no-code, always up-to-date RAG server for any vector database — built on
the Pathway Live Data Framework.**
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
(GitHub or LinkedIn sign-in). Every
command below expects it in PATHWAY_LICENSE_KEY.
Try it in four commands:
**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 (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.
One command to a live RAG stack — then edit a document and watch the answer change.
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
re-indexing step for anyone to run or forget.
**What it costs to run.** Two processes (an indexer and a server) and one YAML
file. Embeddings can be computed locally for free; the Pathway license is
free; the only metered component is the optional model API that writes the
answer text, billed per question rather than per document.
**Where your data goes.** Nowhere by default. With the default local
embedder, documents, their embeddings and the index stay on the machine or in
the database you choose; the only thing that leaves is the handful of passages
retrieved for a question, sent to the model API that writes the answer — and
only if you configure one. (Choosing an API embedder instead sends the
document text through that API as well.)
**How mature it is.** serviette is a thin layer over the
Pathway Live Data Framework — the
open-source engine that does the watching, parsing, embedding and writing: in
development since 2022, 60 000+ GitHub stars, in production use at
organisations such as
DB Schenker,
Intel,
NATO,
La Poste,
Transdev and
CMA CGM.
serviette's own numbers are measured, not estimated: indexing
up to 50 GB of text (26 million pages, 17 million files) in constant memory,
retrieval accuracy on a public benchmark (FRAMES), eight vector databases
under integration tests against real instances — all reproducible from this
repository.
**Where it stands today.** It answers one question at a time, from the
current state of the documents. Conversation memory, user accounts and a
hosted offering are not built in yet — and each is a short step from what is
here. If your use case needs one of them, or something else, contact us for a
tailor-made solution:
open an issue, write on
Discord, or email
contact@pathway.com.
The rest of this README is for the person setting it up.
To run it over your own documents, generate a config and start the stack:
(Production deployments run serviette indexer and serviette server
separately — that is what up supervises.)
The server hosts both the web chat UI (on /) and the versioned REST API
(under /api/v1) on one port:
Highlights
- **No code.** Configure everything in one YAML file (or generate it with
serviette wizard).
- **Any vector DB — 8 backends.** DuckDB (embedded, zero setup — the default),
pgvector, Qdrant, Milvus, ChromaDB, Weaviate, Pinecone and MongoDB Atlas
Vector Search. Every backend is written through **Pathway's native
connectors**, so file edits and deletions become real upserts/deletes in
the store.
- **Zero-setup default.** DuckDB is the default backend: an embedded
database in a single local file, no external service to install or run,
with built-in vector search.
- **Live & incremental.** Built on Pathway: additions, edits and deletions
are reflected in the vector DB in real time — whatever you change is
answerable seconds later. Documents flow through the pipeline instead of
accumulating in it, so a large corpus stays small in memory.
- **Multiple sources.** Local filesystem, Google Drive, S3/MinIO, SharePoint