ML Application · TypeScript

dialoqbase-I6eL

Petr Sovadina@petrsovadina · Atlas 68.5 · #6 builder

View on GitHub Open Petr Sovadina's Atlas

What it is

Dialoqbase is a full-stack open-source chatbot application that lets users create custom chatbots with personalized knowledge bases using various LLMs and embedding models, backed by PostgreSQL for vector search and deployed via Docker.

Scored from the code at its last scan, 23 Oct 2026. How merit is scored

Where it counts

Machine Learning90%
NLP & LLMs90%
MLOps30%
Data Science20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

31bf16-4-3-overshoot-ratio-investigationTraining Experiment · PythonThe repository investigates the effect of different parameter writing rules (e.g., bfloat16 stochastic vs. round-to-nearest-even) on the overshoot ratio in optimizer steps by replaying recorded Camera-3 optimizer captures from Mamba-3 training. It reconstructs the intended…55.5/100ImplementationRickMachine Learning
32, shared rankASTROTraining Experiment · PythonASTRO is a research project developing and evaluating a new optimizer (ASTRO) for language model training, featuring ablation studies, scaling experiments, and a reproducible benchmark harness.55.3/100ImplementationPop AlexandruMachine Learning
32, shared rankdialoqbase-I6eLML Application · TypeScript55.3/100ImplementationPetr SovadinaMachine Learning
34tc-livive-orgEducational Implementation · HTMLThis repository contains an interactive, browser-based learning lab that teaches the concepts of training vs. inference in machine learning using a simple token-counting model. It includes zero-dependency web assets, detailed documentation, and a test runner for generating demos.54.8/100ImplementationJarad PeckenpaughMachine Learning
35ai_chat_distil_01ML Application · HTMLThis repository is a proof-of-concept system for reconstructing speech waveforms for a closed set of phrases using lightweight TensorFlow models. It includes data generation, model training, evaluation, conversion to TensorFlow Lite, and a web dashboard for interaction.54.3/100ImplementationJarad PeckenpaughMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from Petr Sovadina