feat(groq): add support for json_mode

[janzheng]

Description: Added support for Groq's new json_mode for constrained outputs / structured outputs; these ONLY pertain to certain models, but improves consistency dramatically. Docs here: https://console.groq.com/docs/structured-outputs. Also replaced the default Gemma2 test with a llama-3.3-70b-versatile test since Gemma2 is deprecated. Also bumped the groq-sdk to 0.30.0

Dependencies: groq python sdk: https://pypi.org/project/groq/

Tests and Docs: No new tests have been added, but test_chat_models.py default model has been updated to moonshotai/kimi-k2-instruct. Tests are passing.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchain	🛑 Canceled (Inspect)			Aug 4, 2025 8:25pm

[codspeed-hq]

CodSpeed WallTime Performance Report

Merging #32396 will not alter performance

_{Comparing janzheng:master (2beced7) with master (9de0892)}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

✅ 13 untouched benchmarks

[codspeed-hq]

CodSpeed Instrumentation Performance Report

Merging #32396 will not alter performance

_{Comparing janzheng:master (2beced7) with master (9de0892)}

Summary

✅ 14 untouched benchmarks