v0.1.0

What's Changed

• Bump anthropic from 0.28.1 to 0.30.0 by @dependabot in #127
• Add a test case for a single dimension evaluation by @bugsz in #123
• Change the input type of the ReachGoalLLMEvaluator by @bugsz in #129
• Support Azure API for agent and env models; Fix updates on langchain V0.2 by @ruiyiw in #132
• Improve the benchmark by evaluating multiple models and display the results by @bugsz in #126
• Bump litellm from 1.23.16 to 1.40.13 by @dependabot in #125
• background as variable by @XuhuiZhou in #137
• [Automated] Merge release into main by @ProKil in #146
• Bump anthropic from 0.30.1 to 0.31.2 by @dependabot in #139
• finished custom url call by @Jasonqi146 in #142
• Autofix precommit for PRs by @ProKil in #143
• Enabled custom API key for custom OpenAI API by @Jasonqi146 in #154
• Bump types-setuptools from 70.3.0.20240710 to 71.1.0.20240724 by @dependabot in #153
• Bump pytest from 8.2.2 to 8.3.2 by @dependabot in #157
• fix call back handler by @XuhuiZhou in #156
• Fix CI on main by @ProKil in #167
• Bump pydantic from 1.10.12 to 1.10.17 by @dependabot in #168
• Improve the docs and sync with dev by @XuhuiZhou in #166
• Bump mypy from 1.10.1 to 1.11.1 by @dependabot in #162
• Remove all_pks from Sampler.sample by @ProKil in #160
• Bump types-setuptools from 71.1.0.20240806 to 72.2.0.20240821 by @dependabot in #173
• structured output by @XuhuiZhou in #175
• Improvements on benchmark display and usage by @bugsz in #135
• [Automated] Merge release into main by @ProKil in #177
• fix LLM_Name by @XuhuiZhou in #179
• upgrade default model to handle bad-foratted outputs to gpt-4o-mini by @yangalan123 in #183
• [Automated] Merge release into main by @ProKil in #181
• Bump pre-commit from 3.7.1 to 3.8.0 by @dependabot in #161
• Add bad_output_process_model option and use_fixed_model_version option for all generation methods, to avoid future OpenAI API changes break Sotopia running. by @yangalan123 in #196

New Contributors

• @Jasonqi146 made their first contribution in #142
• @yangalan123 made their first contribution in #183

Full Changelog: v0.0.11...v0.1.0