1.0.0

What's Changed

• Add Step abstract class and new Pipeline by @gabrielmbmb in #338
• Add runtime parameters validation by @gabrielmbmb in #345
• Pipeline local execution by @gabrielmbmb in #346
• Add Task (minimal implementation) by @alvarobartt in #347
• Refactor _BatchManager to have list of batches per step by @gabrielmbmb in #353
• Refactor getting parameters from Step.process method by @gabrielmbmb in #355
• Add LLM, OpenAILLM, TransformersLLM, and LlamaCppLLM by @alvarobartt in #354
• Fix Task and TextGeneration by @alvarobartt in #356
• Add combine_dicts function and CombineColumns class by @alvarobartt in #358
• Add PushToHub step and fix typing by @alvarobartt in #357
• Add serialization for the new components by @plaguss in #349
• Fix OpenAILLM.api_key due to SecretStr and StepInput wrong imports by @alvarobartt in #359
• Add GlobalStep, fix _BatchManager, and add logging by @alvarobartt in #362
• Migrate vllm to the new API by @plaguss in #361
• Update _BatchManager to work with GlobalSteps and input_batch_size per step by @gabrielmbmb in #366
• Clean up outdated / unused files by @alvarobartt in #369
• Add input_mappings and output_mappings attributes by @gabrielmbmb in #367
• Move batching from Task to LLM, fix vLLM.generate and add DISTILABEL_LOG_LEVEL by @alvarobartt in #371
• Improve runtime parameter definition by @gabrielmbmb in #372
• Add AsyncOpenAI and update OpenAILLM accordingly by @alvarobartt in #381
• Update serde by @gabrielmbmb in #382
• Add MistralLLM and add generation_kwargs as RuntimeParameters by @alvarobartt in #383
• Move steps out of pipeline by @gabrielmbmb in #384
• Add tests and docstring for Task and subclasses by @alvarobartt in #385
• Add step decorator by @gabrielmbmb in #387
• Add input propagation through Task.process by @alvarobartt in #399
• Improve Pipeline error handling by @gabrielmbmb in #400
• Fix combine_dicts and StepInput import in PushToHub by @alvarobartt in #401
• Improve GlobalStep error handling by @gabrielmbmb in #402
• Changed " by italics in EvolInstruct tutorial where one "" was missing by @ignacioct in #398
• Add get_last_hidden_states method and update TransformersLLM by @gabrielmbmb in #414
• docs: correct small typos in tutorial by @sdiazlor in #419
• docs: readme positioning by @davidberenstein1957 in #386
• Add num_generations and group_generations parameters to Task by @gabrielmbmb in #416
• Add Argilla and PromptCompletionToArgilla by @alvarobartt in #420
• Add EvolInstruct and EvolInstructGenerator tasks by @alvarobartt in #407
• Wrap optional LLM dependencies under load by @alvarobartt in #428
• Add ComplexityScorer task by @gabrielmbmb in #421
• Implement caching mechanism for the pipelines by @plaguss in #370
• Add method to Pipeline to handle keyboard interruptions via ctrl+c by @plaguss in #406
• Add GenerateEmbeddings task by @gabrielmbmb in #427
• Add api_key within LLM.load and add llm_kwargs as RuntimeParameter by @alvarobartt in #432
• Add GeneratorStep.process validation in DAG and smaller fixes by @alvarobartt in #435
• Add EvolComplexity task by @davidberenstein1957 in #415
• Add QualityScorer Task by @ignacioct in #425
• Add CudaDevicePlacementMixin class by @gabrielmbmb in #436
• Return distiset from Pipeline.run by @plaguss in #417
• Update README.md by @strickvl in #451
• Add InferenceEndpointsLLM by @alvarobartt in #439
• Fix Distiset after PushToHub and smaller fixes by @alvarobartt in #452
• Fix Step.process_applying_mappings by @alvarobartt in #453
• Add AnyscaleLLM by @davidberenstein1957 in #447
• Add general function to obtain schema for parquet writer by @plaguss in #454
• Add TogetherLLM by @davidberenstein1957 in #449
• Fix LLM subclasses based on OpenAILLM by @alvarobartt in #455
• Improve batching and caching by @gabrielmbmb in #457
• Add EvolQuality task by @davidberenstein1957 in #429
• Add VertexAILLM by @davidberenstein1957 in #445
• Add use_cache to BasePipeline by @plaguss in #463
• Add AnthropicLLM by @sdiazlor in #444
• Add multiprocess dependency by @gabrielmbmb in #467
• Add UltraFeedback by @alvarobartt in #464
• Add OllamaLLM by @davidberenstein1957 in #405
• Add RuntimeParametersMixin and LLM runtime parameters by @gabrielmbmb in #466
• Add LiteLLM by @davidberenstein1957 in #441
• Add CLI by @gabrielmbmb in #471
• Set _batch_manager to None after run by @gabrielmbmb in #473
• Add create_distiset function by @plaguss in #480
• Add overload to step decorator by @gabrielmbmb in #474
• Move Enum to Dict[str, str] to avoid serialization errors during caching by @plaguss in #482
• Include a dataset card and the pipeline.yaml on Distiset.push_to_hub by @plaguss in #479
• Add PairRM task for ranking responses by @plaguss in #450
• Update _WriteBuffer to write several parquet files by @gabrielmbmb in #483
• Extend Argilla integration TextGeneration, Preference, and more by @alvarobartt in #472
• Add DeitaFiltering step by @gabrielmbmb in #481
• Add InstructionBacktranslation by @alvarobartt in #486
• Fix huggingface_hub TextGenerationError import by @Wauplin in #485
• Improve azure openai support by @BramVanroy in #461
• Add SelfInstruct task by @ignacioct in #456
• Use QueueHandler for Pipeline logging by @gabrielmbmb in #489
• Improve _stop and logging by @gabrielmbmb in #491
• Fix creating empty Dataset in create_distiset function by @gabrielmbmb in #492
• Add imports from __init__ modules by @gabrielmbmb in #493
• batch_size and input_batch_size runtime parameters by @gabrielmbmb in #495
• Update serialization method of _BatchManager to write each step on its own file by @plaguss in #496
• Fix asyncio in AsyncLLM to use the running event loop if any by @alvarobartt in #501
• Added authentication header to allow private/gated dataset use by @bjoernpl in https://github.com/argilla-io/distila...

0.6.0

What's Changed

• Fix typo in docstring of to_argilla metrics_ to metric_ by @burtenshaw in #334
• Implement a JSON responding OpenAI LLM as JSONOpenAILLM by @burtenshaw in #331
• Add examples for the deita paper tasks by @plaguss in #329
• Add checkpoint strategy to automatically push to hub by @plaguss in #321
• docs: update tutorials avoid argilla installation error by @sdiazlor in #337
• Fix CustomDataset.load_from_disk with str/Path objects by @plaguss in #341
• Clalrify number of generations produced when using LLMPool in docs by @davanstrien in #339
• Refactor _build_dataset piece for speed by @plaguss in #344
• Fix documentation and type variables in CustomDataset checkpoint methods by @plaguss in #342
• US Spelling and other typo correction on Distilabel tutorials by @ignacioct in #324
• docs: add a tutorial for evolinstruct by @sdiazlor in #327
• Fix Openai api error with OpenAI-compatible providers by @jphme in #351
• Add fix for labels not returned by openai api by @plaguss in #364
• Refactor model availability check in is_serverless_endpoint_available by @davanstrien in #363

New Contributors

• @burtenshaw made their first contribution in #334
• @jphme made their first contribution in #351

Full Changelog: 0.5.0...0.6.0

0.5.0

What's Changed

• fix: Correct import error by @plaguss in #279
• fix: Filter examples for which len generations != len ratings by @plaguss in #284
• feat: Add sentence transformers support for the to argilla method by @davidberenstein1957 in #262
• feat: Add text descriptives support to the to argilla methods by @davidberenstein1957 in #271
• feat: Add to_argilla method to EvolInstructTask generated datasets by @plaguss in #291
• docs: Shorten titles tutorials and update core example by @davidberenstein1957 in #289
• feat: Add new serialization strategy by @plaguss in #288
• feat: Review OllamaLLM and TogetherInferenceLLM by @alvarobartt in #305
• refactor: Remove Metadata for Ratings by @ignacioct in #303
• docs: Add missing VertexAI information within README.md and docs/index.md by @alvarobartt in #308
• feat: Add functionality to push tasks to the HuggingFace hub and download them automatically. by @plaguss in #297
• feat: Add ComplexityScorer and QualityScorer tasks from Deita by @plaguss in #302
• fix: Fix logging visualization of labeller pipelines by @plaguss in #310
• feat: Add Improving Text Embeddings with LLMs tutorial by @alvarobartt in #313
• feat: Add EvolComplexity and EvolQuality by @davidberenstein1957 in #299
• feat: Add validate_prompts method to LLMs to help validating the prompts by @plaguss in #314
• fix: typo in clean an existing preference dataset by @sdiazlor in #312
• feat: Add new column for sft fine tuning with prepare_dataset by @plaguss in #309
• docs: Custom Task Documentation by @ignacioct in #275
• refactor: Align the LLM subclasses args by @alvarobartt in #315
• feat: Include rationale of the model responses on prepare_dataset if available by @plaguss in #317
• feat: Add embedding tutorial to docs by @ignacioct in #319
• feat: Add MistralAILLM by @plaguss in #293
• feat: Use ollama Python client within OllamaLLM by @sdiazlor in #307

Full Changelog: 0.4.0...0.5.0

0.4.0

What's Changed

• docs: Notus end2end example for preference and instruction generation by @ignacioct in #145
• docs: binders anchors by @ignacioct in #235
• feat: Add support for dedicated and serverless inference endpoints via inference API by @philschmid in #238
• docs: Update links to arxiv landing pages rather than PDFs by @davanstrien in #249
• feat: add ETA to progress bar and fix not showing the progress bar if irrelavant by @ignacioct in #253
• feat: Add Evol instruct task by @plaguss in #237
• docs: rename enable_checkpoints to checkpoint_strategy by @davidberenstein1957 in #257
• feat: Fixing progress bar and ETA by @ignacioct in #260
• fix: resolved error with self instruct to argilla method by @plaguss in #265
• chore: Add extra check in llmpool to ensure all the tasks share the same parent class by @plaguss in #266
• fix: fix for Notus tutorial after bug in record unwrap by @ignacioct in #267
• feat: add customizable criteria for query generation in SelfInstructTask by @ignacioct in #269
• docs: add a tutorial on "clean a DPO/preference dataset with distilabel" by @sdiazlor in #270
• feat: Add new functionality to binarize preference datasets directly from distilabel by @plaguss in #264
• feat: add support ollama api by @davidberenstein1957 in #250

New Contributors

• @philschmid made their first contribution in #238
• @davanstrien made their first contribution in #249
• @sdiazlor made their first contribution in #270

Full Changelog: 0.3.0...0.4.0

0.3.0

What's Changed

• Add VertexAILLM & VertexAIEndpointLLM classes by @gabrielmbmb in #204
• Add draft with social cards by @plaguss in #197
• Relax LLMPool check to match parent Task instead by @plaguss in #210
• Align README.md with docs/ and minor fixes / improvements by @alvarobartt in #214
• Add TogetherInferenceLLM by @alvarobartt in #215
• Add checking valid inputs before calling _generate by @gabrielmbmb in #216
• Add TogetherInferenceLLM tests by @alvarobartt in #217
• Add Vertex AI LLMs documentation by @gabrielmbmb in #222
• Documentation review by @alvarobartt in #223
• Rename for_text_quality to for_overall_quality method in UltraFeedbackTask by @alvarobartt in #224
• Add Anyscale endpoints by @plaguss in #213
• Feature dataset checkpoint strategy by @plaguss in #194
• Fix rating parsing in RatingToArgillaMixin.to_argilla_record by @alvarobartt in #227
• Add badges to readme by @plaguss in #226
• Fix badges by @dvsrepo in #228
• Update LICENSE and add LICENSE_HEADER by @davidberenstein1957 in #221

Full Changelog: 0.2.1...0.3.0

0.2.1

What's Changed

• Fix PrometheusTask could not be imported by @gabrielmbmb in #190
• Fix LLM.return_futures by @gabrielmbmb in #192
• Remove learn section from docs until developed by @plaguss in #188
• Add markdown to fields by default by @plaguss in #189
• Fix PrometheusTask and UltraCMTask could not be chained with TextGenerationTask by @gabrielmbmb in #195
• Add missing use_markdown for every field by @plaguss in #196
• Add to_argilla_{dataset,record} for CritiqueTask by @gabrielmbmb in #198
• Update generate_prompt in Task subclasses to always return Prompt by @alvarobartt in #199
• Add CritiqueTask documentation by @alvarobartt in #200
• Fix UltraCMTask scoring range and align argilla imports by @alvarobartt in #201

Full Changelog: 0.2.0...0.2.1

0.2.0

What's Changed

• adds accelerate example by @edbeeching in #141
• Add a dry-run when calling Pipeline.generate by @alvarobartt in #146
• Add Notus format in Prompt.format_as and update examples/*.py by @alvarobartt in #147
• Add ProcessLLM class by @gabrielmbmb in #151
• Adds CritiqueTask, UltraCMTask and more by @alvarobartt in #152
• docs: add llama.cpp to extras by @davidberenstein1957 in #154
• Fix _build_dataset as processed_labels were ignored by @plaguss in #158
• Add to_argilla_{dataset,record} methods in TextGenerationTask by @alvarobartt in #159
• Fix UltraFeedbackTask.to_argilla_dataset ratings values by @alvarobartt in #160
• Align typing and typing_extensions with supported Python versions by @alvarobartt in #161
• Add LLMPool class by @gabrielmbmb in #156
• Add missing CritiqueTask and UltraCMTask in __init__ and move argilla_utils to utils.argilla by @alvarobartt in #162
• Add test workflow by @gabrielmbmb in #163
• Update LLM to return Future[List[List[LLMOutput]]] by @gabrielmbmb in #164
• Add PrometheusTask by @alvarobartt in #165
• Randomise generations order by @gabrielmbmb in #167
• Add custom to_argilla_{dataset,record} to SelfInstructTask by @alvarobartt in #169
• Fix shuffle_before_labelling and progress bar in Pipeline.generate by @alvarobartt in #170
• Replace multiprocessing with multiprocess by @gabrielmbmb in #171
• Refactor and improve docs by @plaguss in #134
• Fix SelfInstructTask.{parse_output,to_argilla_record} methods and _build_dataset by @alvarobartt in #172
• Fix results didn't have same order as futures by @gabrielmbmb in #173
• Remove unnecesary plugin by @plaguss in #174
• Add {generation,labelling}_model column as metadata in Argilla by @alvarobartt in #175
• Fix exporting model name to Argilla with LLMPool by @gabrielmbmb in #177
• Update docs to include info about ProcessLLM and LLMPool by @gabrielmbmb in #176

New Contributors

• @edbeeching made their first contribution in #141
• @davidberenstein1957 made their first contribution in #154

Full Changelog: 0.1.1...0.2.0

0.1.1

What's Changed

• Template for Documentation Issue created by @ignacioct in #128
• self.thread_pool_executor can be None, protecting it for print by @ignacioct in #129
• Use do_sample in transformers example by @dvsrepo in #138
• Fix llama-cpp and hf-inference-endpoints extras in pyproject.toml by @plaguss in #139
• Fix llama_cpp_python dependency check by @plaguss in #140

New Contributors

• @ignacioct made their first contribution in #128
• @plaguss made their first contribution in #139

Full Changelog: 0.1.0...0.1.1

0.1.0

Stable Release - v0.1.0

0.1.0rc2

distilabel 0.1.0rc2