Lots of new features and bug fixes :)

What's Changed

• Adding Caching to OpenAI chat by @adamgordonbell in https://github.com/guidance-ai/guidance/pull/603
• Minor Server Tweaks by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/612
• Dependency trimming by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/613
• Add Python 3.12 by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/623
• Grammar Builder for JSON Schema by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/619
• remove unused code by @paulbkoch in https://github.com/guidance-ai/guidance/pull/629
• fix: missing tokenizer choice in AzureOpenAI subclasses by @imarquart in https://github.com/guidance-ai/guidance/pull/641
• Pop first argument from guidance wrapper by @hudson-ai in https://github.com/guidance-ai/guidance/pull/634
• Fix behavior of _json_schema_to_grammar for schemas with many properties by @hudson-ai in https://github.com/guidance-ai/guidance/pull/645
• Exclude tests packages from distribution by @shawnz in https://github.com/guidance-ai/guidance/pull/646
• Support multiple additions to ModelStream by @shawnz in https://github.com/guidance-ai/guidance/pull/639
• Enable AzureOpenAI model testing by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/514
• CI Build Schedule by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/662
• Add extensible tests to transformers by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/663
• Update _llama_cpp.py to use new bindings by @Nking92 in https://github.com/guidance-ai/guidance/pull/665
• Propagate errors in ModelStream by @shawnz in https://github.com/guidance-ai/guidance/pull/640
• Fix test_transformers.py by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/673
• Together.ai Support by @minosvasilias in https://github.com/guidance-ai/guidance/pull/654
• Move get_logits and EngineCallResponse out of the Engine.call function so that the remaining parts can be lowered to Rust or C++ in the future and for simplification of LLM servers that operate in batches by @paulbkoch in https://github.com/guidance-ai/guidance/pull/647
• Make Nulls Terminal by @hudson-ai in https://github.com/guidance-ai/guidance/pull/679
• [Test] Expand to other OSes by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/680
• JSON Schema Rewrite by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/651
• [Test] MacOS Issue with Server tests by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/684
• Support mutual recursion in GrammarFunctions by @hudson-ai in https://github.com/guidance-ai/guidance/pull/683
• More JSON schema features by @hudson-ai in https://github.com/guidance-ai/guidance/pull/685
• Improve negative test cases for JSON generation by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/693
• Separate out server tests by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/688
• Add fixture for an LLM by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/674
• Removed side effect on the stop argument from _gen by @VincentToups in https://github.com/guidance-ai/guidance/pull/677
• Fix for test_gen by @riedgar-ms in https://github.com/guidance-ai/guidance/pull/695
• Fix #681 and #682 by @slundberg in https://github.com/guidance-ai/guidance/pull/704

New Contributors

• @adamgordonbell made their first contribution in https://github.com/guidance-ai/guidance/pull/603
• @imarquart made their first contribution in https://github.com/guidance-ai/guidance/pull/641
• @hudson-ai made their first contribution in https://github.com/guidance-ai/guidance/pull/634
• @shawnz made their first contribution in https://github.com/guidance-ai/guidance/pull/646
• @Nking92 made their first contribution in https://github.com/guidance-ai/guidance/pull/665
• @minosvasilias made their first contribution in https://github.com/guidance-ai/guidance/pull/654
• @VincentToups made their first contribution in https://github.com/guidance-ai/guidance/pull/677

Full Changelog: https://github.com/guidance-ai/guidance/compare/0.1.11...0.1.12