deeppavlov/AutoIntent

📋 What's Changed

• See details at [CHANGELOG.md](https://github.com/deeppavlov/AutoIntent/blob/dev/CHANGELOG.md#031--2026-06-16).
• tmp fix for faiss typing by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/292
• fix: update tunable decision test for optuna 4.9 by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/293
• Fix/hf rate limit on tests by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/294
• ci: bump GitHub Actions to Node 24 versions by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/300
• test: mock live-API tests (no live OpenAI/OpenSearch in CI) by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/301
• fix(llm-scorer): persist generator_config across dump/load roundtrip by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/302
• fix(tests): restore pipeline interruption tests after sampler API removal by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/303
• + 6 more

📋 What's Changed

• See details at [CHANGELOG.md](https://github.com/deeppavlov/AutoIntent/blob/dev/CHANGELOG.md).
• Update conf.py by @Samoed in https://github.com/deeppavlov/AutoIntent/pull/255
• Feat/mcp interface by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/260
• Feat/open search by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/259
• Refactor/migrate to uv by @voorhs in https://github.com/deeppavlov/AutoIntent/pull/257
• feat/train-embeddings by @k0lenk4 in https://github.com/deeppavlov/AutoIntent/pull/246
• Feat/gcn scorer by @SeBorgey in https://github.com/deeppavlov/AutoIntent/pull/261
• adversarial augmentation by @Tetragrammaton123 in https://github.com/deeppavlov/AutoIntent/pull/251
• + 19 more

✨ New Contributors

• @k0lenk4 made their first contribution in https://github.com/deeppavlov/AutoIntent/pull/246
• @Tetragrammaton123 made their first contribution in https://github.com/deeppavlov/AutoIntent/pull/251
• Full Changelog: https://github.com/deeppavlov/AutoIntent/compare/v0.2.0...v0.3.0

✨ New Scorers

• bert, lora, peft - by @voorhs, @SeBorgey, @nikiduki, @riapush
• rnn, cnn - by @voorhs, @SeBorgey
• catboost - by @Samoed, @nikiduki
• zero shot methods (bi encoder, cross encoder, llm) - by @voorhs, @Darinochka

📦 AutoML

• optimization presets by @voorhs
• refactor HPO schema by @voorhs
• autointent interruption handling by @Samoed

📦 Other

• node validation by @Samoed
• codecarbon callback by @Darinochka, @Samoed

📦 Chores

• updated docs and tutorials by @voorhs
• optimized tests for repo by @Samoed
• innumerable bugs fixes by @voorhs, @Samoed
• Full Changelog: https://github.com/deeppavlov/AutoIntent/compare/v0.1.0...v0.2.0

✨ New functionality

• optuna samplers: TPE, Random, Brute
• cross-validation (previously: only hold-out validation)
• basic presets for balancing between the quickness and the quality
• logging to wandb and tensorboard
• LLM-based augmentation strategies for enriching your training data

📦 Improvements

• better regular expressions support
• better UX on conducting experiments
• more convenient way to dump fitted pipeline to disk and then load it for inference

📝 Documentation

• Check out our updated user guides!

✨ Features

• Library of intent classification methods:
• regexp module for rule-based classification
• proxy tuning hyperparams of embedding model using retrieval metrics
• scoring modules for predicting intents probabilities
• decision-making modules for constructing final prediction for multi-class and multi-label classification and out-of-domain detection
• Auto ML approach to creating intent classifier:
• greedy optimization for tuning hyperparameters
• no target leakage, thanks to hold-out validation
• + 4 more

📝 Documentation

• API Reference for all modules, metrics and etc
• User guides with basic and advanced usage both for Python API and CLI
• Theoretical sections on dialogue systems creation and key concepts of AutoIntent