v0.1.27

What's New

Tinker Integration for Fine-tuning (#710)

• Added support for Tinker SDK integration, enabling LoRA fine-tuning directly after generating data with Curator. When a TINKER_API_KEY is provided, training runs against the Tinker service with real
  forward/backward passes. Features include:
• Checkpointing support (per-epoch and per-N-steps) with dashboard visibility
• Gradient accumulation, LoRA alpha/dropout/target_modules configuration
• Checkpoint resume support
• Falls back to mock mode when SDK/key is not available
• New examples in examples/tinker/ and examples/poem_finetuning_example.py

Claude 4.x and 3.7 Model Support (#704)

Added multimodal and JSON format support for new Anthropic models:

• Claude 4.5 (Sonnet, Haiku, Opus)
• Claude 4.0/4.1 (Sonnet, Opus)
• Claude 3.7 Sonnet

Bug Fixes

• Fixed LiteLLM multi-hosted_vllm request address mixture (#701) — Resolved an issue where requests could be routed to the wrong vLLM host when using multiple hosted_vllm backends.
• Fixed broken tests (#706)

Other Changes

• Code cleanup in OpenAI online request processor (#708)
• README updates (#707)

v1.0.26

What's Changed

• fix: viewer url bug in curator response by @kartik4949 in #682
• feat: add support to download dataset from viewer by @kartik4949 in #652
• If the model is not known, let the cost be None. by @madiator in #681
• feat: add stopping criteron in agent by @kartik4949 in #684
• fix error when torch isn't installed by @shreyaspimpalgaonkar in #663
• ref: check structured outputs support with litellm by @kartik4949 in #683
• Ref agent multiturn minor by @kartik4949 in #685
• chore: bump 0.1.26 by @kartik4949 in #686
• fix: resolve Pydantic issues by @emmanuel-ferdman in #689
• feat: auto batch mode by @kartik4949 in #691
• ref: add version tag in lib by @kartik4949 in #696

Full Changelog: v0.1.25...v0.1.26

v0.1.25

What's Changed

• docs: clean up wording in README by @vutrung96 in #662
• Feat/openai/deepseek api by @fenglui in #640
• Fix/curator-cli-batch-update-freq-increase by @CharlieJCJ in #632
• feat: add example of prescription extraction by @kartik4949 in #661
• fix: migrate to logger.warning by @emmanuel-ferdman in #666
• perf: make download batch lazy in gemini processor by @kartik4949 in #654
• Feat/agentic/multiturn by @kartik4949 in #658
• update agentic multi turn example by @kartik4949 in #667
• Clean up _factory.py by @madiator in #668
• updated examples by @kartik4949 in #670
• feat: add response object in agent by @kartik4949 in #671
• make agentic curation response format as openai by @kartik4949 in #673
• Feat/add/curator/link/agent by @kartik4949 in #672
• Delete HOSTED_CURATOR_VIEWER environment variable. by @madiator in #674
• Add o3 to list of models supporting structured outputs by @madiator in #679
• chore: bump 0.1.25 by @kartik4949 in #680

New Contributors

• @fenglui made their first contribution in #640
• @emmanuel-ferdman made their first contribution in #666

Full Changelog: v0.1.24...v0.1.25

v0.1.24

What's Changed

• fix: multiple bugs in batch cancellation by @vutrung96 in #614
• bump version and remove curator viewer related release code by @vutrung96 in #627
• fix/curator CLI display - rpm display and frequent tqdm update for tqdm for online by @CharlieJCJ in #629
• Fix/deepseek/rpm by @kartik4949 in #630
• Update README to add new updates and a better example by @madiator in #628
• improve projected total, projected remaining UI in online by @CharlieJCJ in #631
• update metadata schema with cost by @kartik4949 in #626
• feat: add param to disable metadata db by @shreyaspimpalgaonkar in #583
• add gpt 4.1 structured output support from curator by @CharlieJCJ in #637
• feat: fix batch mode structure outputs bug by @kartik4949 in #639
• cost streaming in batch mode and delayed streaming support by @kartik4949 in #638
• Add gpt-4.1 structured output support by @Mithil467 in #642
• fix/final_statistics_display_fixes by @CharlieJCJ in #644
• feature: set dtype flag by @sky-2002 in #645
• Fix casting issue in token accounting with anthropic by @RyanMarten in #649
• ref: check job state before download in gemini by @kartik4949 in #646
• ref: support anthropic backend for multimodal input by @kartik4949 in #656
• chore: bump 0.1.24 by @kartik4949 in #659
• feat: add response object in curator by @kartik4949 in #643
• docs: updated README with information about authentication by @vutrung96 in #660

New Contributors

• @Mithil467 made their first contribution in #642
• @sky-2002 made their first contribution in #645

Full Changelog: v0.1.23...v0.1.24

v0.1.23.post1

What's Changed

• fix: multiple bugs in batch cancellation by @vutrung96 in #614

Full Changelog: v0.1.23...v0.1.23.post1

v0.1.23

What's Changed

• Adding Mistral batch to examples/providers by @sarthakwer in #609
• Feat/retry/batch by @kartik4949 in #585
• Feat/recipe/simplestrat by @kartik4949 in #598
• Update curator rich cli gif by @CharlieJCJ in #617
• remove split from card template by @davanstrien in #619
• feat/env-disable-rich-cli by @CharlieJCJ in #600
• update config map for kluster by @shreyaspimpalgaonkar in #620
• feat: fix gemini batch parts key missing by @kartik4949 in #612
• Add llama4 models from klusterAI by @shreyaspimpalgaonkar in #622
• feat: add failed requests jsonl by @kartik4949 in #615
• Feat/openai/deepseek api by @kartik4949 in #579
• Disable loud log by @RyanMarten in #624
• fix: add finish reason in gemini batch by @kartik4949 in #621
• bump 0.1.23 by @kartik4949 in #625

New Contributors

• @sarthakwer made their first contribution in #609

Full Changelog: v0.1.22...v0.1.23

v0.1.22

What's Changed

• bump: 0.1.21 by @vutrung96 in #595
• Update citation in zh, and move some files to docs folder. by @madiator in #596
• Add a table of examples. by @madiator in #597
• Add one more tutorial and organize the examples better. by @madiator in #601
• ref: update gemini example by @kartik4949 in #602
• Fix/live colab display error by @CharlieJCJ in #599
• feat: implement Mistral batch request processor by @Saharsh1005 in #584
• If the input is a string or a list of strings for prompt(), maintain the same for parse() by @madiator in #604
• Delete the local curator viewer and rename variable HOSTED_CURATOR_VIER by @madiator in #605
• ref: make prapogate false in logger by @kartik4949 in #590
• feat: add authentication flow in curator client by @kartik4949 in #606
• chore: bump version (0.1.22) by @kartik4949 in #608

New Contributors

• @Saharsh1005 made their first contribution in #584

Full Changelog: v0.1.21...v0.1.22

v0.1.21

What's Changed

• fix: publish package install command by @RyanMarten in #555
• add max in progress (concurrent request) in online status tracker by @CharlieJCJ in #568
• fix: make process_response mandatory in create_dataset files by @kartik4949 in #574
• Cost Estimation revamp [1/n] Online processors by @CharlieJCJ in #546
• Ref/push to viewer by @kartik4949 in #576
• Ref/update/ratelimits/gemini by @kartik4949 in #578
• fix: use model name from config in cost processor by @kartik4949 in #575
• feat: extract mime_type in Image types by @kartik4949 in #582
• Feat/raft by @kartik4949 in #571
• Update README.md by @madiator in #587
• Ensure that when a list or a string is passed without a dictionary, we handle it appropriately. by @madiator in #588
• Add o3-mini models as a supported model series for structured output. by @madiator in #593
• fix: use semaphore to gate create new rows to prevent OOMs by @vutrung96 in #591
• Cleaup: Minor refactoring. by @madiator in #592
• bug: wrap estimate tokens with int in litellm backend and mime type fix. by @kartik4949 in #586
• fix: output unicode directly for gemini batch processor by @vutrung96 in #594

Full Changelog: v0.1.20...v0.1.21

v0.1.20

What's Changed

• Update README.md to add code execution launch news by @madiator in #547
• Update README.md by @RyanMarten in #551
• Feat/resume/hosted curator viewer by @kartik4949 in #533
• ref: add gen params in testcall litellm backend by @kartik4949 in #552
• Claude 3.7 Reasoning by @RyanMarten in #536
• 0.1.20 release by @RyanMarten in #554

Full Changelog: v0.1.19.post1...v0.1.20

v0.1.19.post1

What's Changed

• Update badges by @RyanMarten in #501
• Update README.md to stop kluster.ai promo by @madiator in #514
• ref: summarize errors in online mode by @kartik4949 in #515
• Rich hyperlink for curator viewer by @CharlieJCJ in #516
• fix: expanduser in telemetry random id creationg by @kartik4949 in #530
• Update/litellm by @kartik4949 in #509
• Code executor enhancements + tests by @shreyaspimpalgaonkar in #495
• modify telemetry config by @shreyaspimpalgaonkar in #502
• Feat/logger by @kartik4949 in #518
• Feat/push to viewer by @kartik4949 in #520
• Fix curator tag by @RyanMarten in #539
• Minor changes to code executor by @madiator in #541
• update examples and minor fix to docker backend by @shreyaspimpalgaonkar in #540
• bump version by @shreyaspimpalgaonkar in #545
• ref: make batch response file method async by @kartik4949 in #532

Full Changelog: 0.1.19...v0.1.19.post1