langsmith-sdk

What's Changed

• Improve Error Handling of Middle Copy by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/759

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.68...v0.1.69

What's Changed

• safer exception by @hwchase17 in https://github.com/langchain-ai/langsmith-sdk/pull/758

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.67...v0.1.68

What's Changed

• [Python] Infer parent_run_id in from_dotted_order by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/754

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.66...v0.1.67

What's Changed

• fix(js): add missing callbacks when evaluating a runnable by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/748
• [Python] Handoff Bugs by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/753

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.65...v0.1.66

What's Changed

• [Python] Update RunnableConfig <> RunTree Precedence by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/747

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.64...v0.1.65

What's Changed

• Fix typo in feedback client by @HoangNguyen689 in https://github.com/langchain-ai/langsmith-sdk/pull/727
• feat(js): add distributed tracing by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/740
• Fix tracing for as_runnable by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/745
• Read parent run info from RunnableConfig if passed to function decorated with traceable by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/746

New Contributors

• @HoangNguyen689 made their first contribution in https://github.com/langchain-ai/langsmith-sdk/pull/727

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.63...v0.1.64

What's Changed

• implement repetitions in js and python by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/724

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.62...v0.1.63

What's Changed

• Add method to create multiple presigned feedback urls in one call by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/725
• chore(deps): bump requests from 2.31.0 to 2.32.2 in /python by @dependabot in https://github.com/langchain-ai/langsmith-sdk/pull/723
• [Python] Release by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/726

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.61...v0.1.62

What's Changed

• chore(js): reexport TraceableFunction type from singleton by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/716
• chore(js): make sure we use "type": "text" for invocation params tracking by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/718
• feat(js): move getLangchainCallbacks to TypeScript SDK by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/719
• feat(python): append invocation params when using wrap_openai by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/717
• fix(handoff): support streaming returned generators by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/708
• chore(js): Bump version to 0.1.28 by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/713
• [Python] Add Null Sentry by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/722

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.60...v0.1.61

What's Changed

• feat(ts): add invocation params handling in wrapOpenAI by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/707
• fix(js): LangChain / traceable handoff by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/678
• feat(datasets): Allow multiple splits per example, add splits to experiment metadata on evaluation by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/709
• fix(js): populate this._experiment when creating a new project by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/714
• fix: bump 0.5.7 by @langchain-infra in https://github.com/langchain-ai/langsmith-sdk/pull/715

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.59...v0.1.60

What's Changed

• [Py] Ignore optional numpy import by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/700
• fix: bump 0.5.1 by @langchain-infra in https://github.com/langchain-ai/langsmith-sdk/pull/704
• Add splits as param to list_examples, create_example/s, update_example (and typescript equivs) by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/702

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.58...v0.1.59

What's Changed

• feat(pairwise): show URL in console by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/679
• feat(pairwise): allow passing evaluator directly to wait for evaluation to complete by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/681
• feat(pairwise): trace evaluators in evaluateComparitive by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/682
• Make traceable not throw error in deno by using node: imports by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/689
• chore(js): 0.1.24 by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/688
• js[patch]: Fix listRuns limit arg by @bracesproul in https://github.com/langchain-ai/langsmith-sdk/pull/668
• fix(js): make sure evaluator run ID is propagated properly by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/691
• fix(js): e2e tests failing for limit by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/693
• fix(js): evaluator runs traced in experiment project than in evaluators project by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/690
• chore[js]: bump JS to 0.1.25 by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/694
• fix[js]: print stack trace when error occur in evaluate by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/695
• chore[ts]: expose RetrieverOutput type by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/696
• feat[js]: add view URL to the experiment when running evaluate by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/697
• fix: use 0.5.0 image by @langchain-infra in https://github.com/langchain-ai/langsmith-sdk/pull/701

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.57...v0.1.58

What's Changed

• feat(js): trace deferred values in input by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/662
• fix(ci): incorrect secret pulled in integration tests by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/676
• fix(sdk): remove API key by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/674
• fix(js): add support for tracing generators in input and output by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/660
• Clarify docstring for randomize_order by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/675
• feat(ts): evaluateComparative by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/673
• fix(ts): too strict TargetT type by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/683
• feat: release 03.5 docker compose by @langchain-infra in https://github.com/langchain-ai/langsmith-sdk/pull/685

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.56...v0.1.57

What's Changed

• feat(pairwise evals): add option to randomize order of experiments; print URL for pairwise experiment by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/672

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.55...v0.1.56

What's Changed

• feat(js): add hasDataset function by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/658
• fix(js): serialization of run tree if found in evaluate as input by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/656
• fix(js): throw when wrapping same client twice, allow passing name in argsConfigExtra by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/663
• chore(js): release 0.1.23 by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/667
• Bump tqdm from 4.66.2 to 4.66.3 in /python by @dependabot in https://github.com/langchain-ai/langsmith-sdk/pull/669
• Implement evaluate_comparative for comparing the results of multiple experiments by @samnoyes in https://github.com/langchain-ai/langsmith-sdk/pull/651

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.54...v0.1.55

What's Changed

• chore(ci): add unit test matrix for 21.x and 22.x by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/653
• fix(traceable): async iterators lose context by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/652
• fix(js): store execution order number in dotted order by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/654
• fix(js): allow passing run tree manually by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/648
• Add Experiment Description Support by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/657

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.53...v0.1.54

What's Changed

• Upgrade typescript to 5.4.5 by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/639
• Fix traceable and wrapOpenAI by @nfcampos in https://github.com/langchain-ai/langsmith-sdk/pull/640
• [JS] Bump Version by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/641
• JS[major]: Evaluate by @bracesproul in https://github.com/langchain-ai/langsmith-sdk/pull/621
• fix(py): allow metadata to be a dict in list_examples by @agola11 in https://github.com/langchain-ai/langsmith-sdk/pull/647
• feat(JS): allow fetching examples by metadata by @agola11 in https://github.com/langchain-ai/langsmith-sdk/pull/646
• [Python] 0.1.53 by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/650

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.52...v0.1.53

What's Changed

• Allow for passing metadata into the wrapOpenAI method by @jacoblee93 in https://github.com/langchain-ai/langsmith-sdk/pull/628
• Allow aggregator for streamed chunks to be passed to traceable in TS by @jacoblee93 in https://github.com/langchain-ai/langsmith-sdk/pull/629
• Adds streaming aggregation for OpenAI, fix metadata passing by @jacoblee93 in https://github.com/langchain-ai/langsmith-sdk/pull/633
• [JS] 0.1.19 by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/634
• js[patch]: Fix lint ci and add lint:fix script by @bracesproul in https://github.com/langchain-ai/langsmith-sdk/pull/632
• Respect env var for tracing in TS by @jacoblee93 in https://github.com/langchain-ai/langsmith-sdk/pull/635
• Fix mock checking in integration tests, wrapSDK and sporadic flakiness by @dqbd in https://github.com/langchain-ai/langsmith-sdk/pull/636
• Add expect.score by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/631

New Contributors

• @bracesproul made their first contribution in https://github.com/langchain-ai/langsmith-sdk/pull/632

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.51...v0.1.52

What's Changed

• Fix Sync Generator Nesting by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/627

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.50...v0.1.51

What's Changed

• Add support for handling pytest.skip in @unit by @hinthornw in https://github.com/langchain-ai/langsmith-sdk/pull/623

Full Changelog: https://github.com/langchain-ai/langsmith-sdk/compare/v0.1.49...v0.1.50