2.5.3

What's Changed

• fix(dspy): bug fix for snowflake retriever caused by smart filter update by @sfc-gh-alherrera in #1565
• [1] DatabricksRM: Use databricks-sdk to fetch token / workspace URL + several small improvements by @dbczumar in #1564

Full Changelog: 2.5.2...2.5.3

2.5.2

What's Changed

• Fixing typed predictors for 2.5 with a temporary _parse_values=False … by @okhat in #1558
• Improve o1 support in dspy.LM (QoL errors) by @okhat in #1559

Full Changelog: 2.5.1...2.5.2

2.5.1

What's Changed

• Make output processing in typed predictors compatible to dspy.LM (2.5) by @krypticmouse in #1546
• Patche python interpreter to support additional syntax by @arnavsinghvi11 in #1550
• Release workflow updated to also publish to dspy as well as dspy-ai on pypi by @hmoazam in #1557

New Contributors

• @bluewin4 made their first contribution in #1542
• @jannikmaierhoefer made their first contribution in #1554

Full Changelog: 2.5.0...2.5.1

2.5.0

What's Changed

• Adapters type casting & enforcement. Migration notebook. by @okhat in #1532
• Add deprecation warning for old clients on first use (per client) by @okhat in #1533
• Pin cached notebooks to 2.4.17 prior to deprecations by @okhat in #1528
• Top-level file cleanup by @okhat in #1529
• Add warning for deep copy by @chenmoneygithub in #1531

Full Changelog: 2.4.17...2.5.0

2.4.17

What's Changed

• Various improvements for adapters & LMs by @okhat in #1523
• MIPROv2(v2) -- Big Updates to the MIPROv2 Optimizer by @XenonMolecule in #1522
• Improve error logging with a stacktrace by @severi in #1458
• Fix dspy Module's deepcopy by @chenmoneygithub in #1519
• Typo/nit fixes and add tests for BoostrapWithRandomSearch by @chenmoneygithub in #1502

New Contributors

• @siddharthsambharia-portkey made their first contribution in #1496
• @NirantK made their first contribution in #1498
• @PrashantDixit0 made their first contribution in #1444
• @jeffreyrubi made their first contribution in #1484
• @manubhardwaj made their first contribution in #1437
• @arya-krishna-23 made their first contribution in #1432
• @severi made their first contribution in #1458

Full Changelog: 2.4.16...2.4.17

2.4.16

This is a pretty significant release. New dspy.LM and dspy.Adapter will be key for DSPy 2.5 onwards. Old clients are unaffected for now.

What's Changed

• Adding new dspy.LM and dspy.Adapter by @okhat in #1486
• Make langchain copy-able in DSPy by @chenmoneygithub in #1488
• feat(dspy): support o1 parameters by @isaacbmiller in #1487

New Contributors

• @rawsh made their first contribution in #1485

Full Changelog: 2.4.15...2.4.16

2.4.15

What's Changed

• Assertions patches by @arnavsinghvi11 in #1471
• Fix misc assertion errors by @Shangyint in #1085
• Fix assertion bug with new_signature by @Shangyint in #1372
• Fix rendering of evaluation results Pandas DataFrames in console environments by @dbczumar in #1472
• Bug Fix: Multiline init regex parsing (MIPROv2) by @XenonMolecule in #1466

New Contributors

• @karthikscale3 made their first contribution in #1456
• @hacker-4-good made their first contribution in #1469
• @dbczumar made their first contribution in #1472

Full Changelog: 2.4.14...2.4.15

DSPy v2.4.14

Update pyproject.toml

DSPy v2.4.13

• supports configurable backoff time for LM/RM providers dspy.settings.configure(backoff_time = ...)
• latest PR changes and updates (Langchain Metaclass resolution, addition of Langchain Tool Execution, MIPROv2 parameter updates, LM/RM Provider updates)

Full Changelog: v2.4.12...2.4.13

DSPy v2.4.12

• Supports treating dspy.Predict and dspy.ChainOfThought directly as Modules, e.g. can compile them without creating a wrapping dspy.Module object.

• Improves the experimental=True Chat LM support from DSPy v2.4.11, which is quoted below for reference:

Initial support for new adapters, with far more smooth support for Chat LMs. The default behavior is unchanged from before. However, dspy.configure(experimental=True) is likely to lead to much more predictable and accurate zero-shot generations with Chat LMs. Tested against several variants of GPT-3.5, GPT-4, Llama3, Mixtral, and DBRX.