Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / RAG & Knowledge / serviette

A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.

Stars58.7k
Forks1.6k
LanguagePython
LicenseNot specified

About this project

serviette is an open-source retrieval and knowledge project on GitHub: A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway. It lives in retrieval and knowledge management, the layer that lets a model answer from your own documents instead of from training data alone. It is maintained by pathwaycom and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged chromadb, document-qa, document-search, duckdb, live-data, llm, milvus, mongodb, no-code, pathway, pgvector and pinecone, which is a fair summary of what it covers. There is normally an ingestion pipeline, an embedding and vector index, and a query layer on top. Most of the engineering effort goes into chunking, ranking and keeping the index fresh as documents change.

It is written mainly in Python and released under MIT, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 11, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 58,708 stars; 1,551 forks; primary language Python; license MIT; last commit on November 11, 2026; topics chromadb, document-qa, document-search, duckdb, live-data, llm.