This is the RadLab Group workspace. Here you will find our publicly available repositories.
Our mission is to propagate open knowledge, software, datasets and models.
Our official website: radlab.dev.
If you want to contact us, feel free to send an email to hello@radlab.dev
Have fun and a nice day! :)
A lightweight, extensible toolkit for preparing, indexing, and querying textual data for semantic search and downstream NLP tasks.
An extensible platform for repeatable evaluation of coding agents, LLM routers, models, and the plugins that extend their capabilities (knowledge bases, routing, optimizations).
Omni‑Mask — offline Python tool that masks PESEL, NIP, phone, address, e‑mail, IBAN, ID numbers and full names in PDF, Word, Excel and text files, generates a reversible mapping key, and includes a simple Tkinter GUI. No internet connection required.
A companion repository for llm-router containing a collection of pipeline-ready plugins. Features a masking interface for anonymizing sensitive data and a guardrail system for validating input/output safety against defined policy rules.
Anonymizer‑model is a lightweight classification‑based solution for automatically detecting and masking personally identifiable information (PII) in text data. The repository contains everything needed to train, evaluate, and serve the model via a simple API.
A hybrid Relational-GAT with a projection head that learns relation operators to transform embeddings, impute unseen node vectors, and expand search queries via relational paths.
Utilities and scripts to transform plWordNet into machine‑learning‑ready artifacts: build graphs, create balanced embedding datasets from lexical relations, split into train/test, and prepare indices for downstream retrieval tasks.
LLM Router is a service that can be deployed on‑premises or in the cloud. It adds a layer between any application and the LLM provider. In real time it controls traffic, distributes a load among providers of a specific LLM, and enables analysis of outgoing requests from a security perspective (masking, anonymization, prohibited content).
The repository contains a view for semantic-search-engine. Its individual components (pages) are used to prepare data (indexing). This is a ready‑to‑use solution for handling RAG.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…
