A local lexical search engine for small document collections. It splits documents into chunks, builds normalized TF-IDF vectors and ranks passages by cosine similarity. Results retain their source, chunk number and matching terms. Educational examples are provided without private data or remote AI dependencies.
Included capabilities
- Local TXT and Markdown files
- Configurable overlapping chunks
- Cosine ranking and matching terms
- Portable JSON index
- Original examples and boundary tests
Licence and getting started
Original code under the MIT licence, copyright 2026 STELLARR STUDIO. Personal and commercial use permitted with the licence notice retained. French and English guides included. Trademarks and dependencies retain their own rights.
Read the README for requirements, start commands, tests and deployment limits. Hosting, compute, external APIs and bespoke support are not included.
Included files
.gitignoreexamples/documents/donnees.txtexamples/documents/interfaces.mdexamples/documents/restauration.mdkit.jsonLICENSEREADME.en.mdREADME.mdsearch.pyTEST_REPORT.mdtest_search.pyTHIRD_PARTY_NOTICES.mdverification.json