-
Notifications
You must be signed in to change notification settings - Fork 31
Comparing changes
Open a pull request
base repository: sotopia-lab/sotopia
base: v0.1.0
head repository: sotopia-lab/sotopia
compare: v0.1.1
- 20 commits
- 69 files changed
- 8 contributors
Commits on Oct 1, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 4bf087d - Browse repository at this point
Copy the full SHA 4bf087dView commit details -
[Automated] Merge release into main (#199)
* bump the version, test release to PyPi * Update README.md * Update README.md * Update README.md * bumpy version to 0.0.9 * Update Sotopia presentation information in README.md * bump version to 0.0.10 * bump version * add merge release back to main action * change checkout v4->v3 * fix merge-back-to-main and pin mypy to <1.11.0 * merge bug fix * upgrade default model to handle bad-foratted outputs to gpt-4o-mini as gpt-3.5-turbo is deprecated (#183) * update pull request -> pull request target * bump version * 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. (#196) * Two major updates: 1) add "bad_output_process_model" option to all `agenerate_xxx()` methods so users can decide which model to use for handling bad outputs. By default, this is set to be `gpt-4o-mini`. 2) add `use_fixed_model_version` option for all generation methods, as some fixed model version may no longer available in the future. Users should have the right to bypass the fixed model version mapping instead of getting stuck in an error. Document (`generation.md`) has been updated for these two major changes correspondingly. * [autofix.ci] apply automated fixes --------- Co-authored-by: Chenghao Yang <yangalan1996@gmail.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> * fix gpt-3.5 * replace gpt3.5 turbo for tests * update gpt-3.5-turbo to gpt-4o-mini * bug fix for return fixed model version function --------- Co-authored-by: XuhuiZhou <zhouxuhui2018@gmail.com> Co-authored-by: Chenghao (Alan) Yang <chenghao@uchicago.edu> Co-authored-by: Chenghao Yang <yangalan1996@gmail.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 785669c - Browse repository at this point
Copy the full SHA 785669cView commit details
Commits on Oct 2, 2024
-
Update Pydantic to v2 and redis-om to v0.3. (#138)
* try updating redis-om and pydantic * update poetry lock * fix all of the issues detected by mypy * migration to v2 * Version conditioned import for `Self` * fixed non-required field errors * update validator apis * fixed the validator bugs --------- Co-authored-by: XuhuiZhou <zhouxuhui2018@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for 2a51167 - Browse repository at this point
Copy the full SHA 2a51167View commit details
Commits on Oct 4, 2024
-
Configuration menu - View commit details
-
Copy full SHA for a7a9adc - Browse repository at this point
Copy the full SHA a7a9adcView commit details -
Configuration menu - View commit details
-
Copy full SHA for 13cccc9 - Browse repository at this point
Copy the full SHA 13cccc9View commit details -
[Automated] Merge release into main (#214)
* bump the version, test release to PyPi * Update README.md * Update README.md * Update README.md * bumpy version to 0.0.9 * Update Sotopia presentation information in README.md * bump version to 0.0.10 * bump version * add merge release back to main action * change checkout v4->v3 * fix merge-back-to-main and pin mypy to <1.11.0 * merge bug fix * upgrade default model to handle bad-foratted outputs to gpt-4o-mini as gpt-3.5-turbo is deprecated (#183) * update pull request -> pull request target * bump version * 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. (#196) * Two major updates: 1) add "bad_output_process_model" option to all `agenerate_xxx()` methods so users can decide which model to use for handling bad outputs. By default, this is set to be `gpt-4o-mini`. 2) add `use_fixed_model_version` option for all generation methods, as some fixed model version may no longer available in the future. Users should have the right to bypass the fixed model version mapping instead of getting stuck in an error. Document (`generation.md`) has been updated for these two major changes correspondingly. * [autofix.ci] apply automated fixes --------- Co-authored-by: Chenghao Yang <yangalan1996@gmail.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> * fix gpt-3.5 * replace gpt3.5 turbo for tests * update gpt-3.5-turbo to gpt-4o-mini * bug fix for return fixed model version function * fix sampling error * fix rc.4 * new tag --------- Co-authored-by: XuhuiZhou <zhouxuhui2018@gmail.com> Co-authored-by: Chenghao (Alan) Yang <chenghao@uchicago.edu> Co-authored-by: Chenghao Yang <yangalan1996@gmail.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 25013e4 - Browse repository at this point
Copy the full SHA 25013e4View commit details -
improve the documentation (#194)
* improve the documentation * Audited and updated introduction * revamp concepts/agent * agent profiles doc * updated agents and environments docs * database and generation docs --------- Co-authored-by: Hao <prokilchu@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for 8568cfb - Browse repository at this point
Copy the full SHA 8568cfbView commit details -
Fix: change hiredis version to >= 3.0.0 (#216)
* change to >= * update poetry lock * typo
Configuration menu - View commit details
-
Copy full SHA for 7f5be99 - Browse repository at this point
Copy the full SHA 7f5be99View commit details
Commits on Oct 7, 2024
-
Adding a devcontainer with Redis and a Ollama server (#217)
* minimal demo example of running custom model * devcontainer setup and example * remove default_bad_process_model to allow using custom model entirely * improve the demo to show parallel execution * CI: update tests trigger from pull request target to pull request * fix mypy errors * adding stubs to pyproject.toml * poetry lock * install all extras in the devcontainer start script * add dev containers instruction * add a link to command palette wiki * adding instructions for dev containers
Configuration menu - View commit details
-
Copy full SHA for 71d6199 - Browse repository at this point
Copy the full SHA 71d6199View commit details
Commits on Oct 8, 2024
-
Migration from Poetry to uv (#218)
* minimal demo example of running custom model * devcontainer setup and example * remove default_bad_process_model to allow using custom model entirely * improve the demo to show parallel execution * CI: update tests trigger from pull request target to pull request * fix mypy errors * adding stubs to pyproject.toml * poetry lock * install all extras in the devcontainer start script * add dev containers instruction * migration to uv * update mypy * Update index.mdx * update uv venv path in the devcontainer and contributor's guide
Configuration menu - View commit details
-
Copy full SHA for ed626ec - Browse repository at this point
Copy the full SHA ed626ecView commit details
Commits on Oct 10, 2024
-
Configuration menu - View commit details
-
Copy full SHA for cd8e636 - Browse repository at this point
Copy the full SHA cd8e636View commit details -
Configuration menu - View commit details
-
Copy full SHA for 781477c - Browse repository at this point
Copy the full SHA 781477cView commit details -
Configuration menu - View commit details
-
Copy full SHA for fbb0fc9 - Browse repository at this point
Copy the full SHA fbb0fc9View commit details
Commits on Oct 11, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 3c4fb2e - Browse repository at this point
Copy the full SHA 3c4fb2eView commit details -
CI: Removing External Service Dependency in CI (#228)
* dockerfile * docker compose (it works) * use published images to speed up * add ci test with docker * use compose action github action * update docker compose file * update compose file path * use github-action-docker-compose-test-run * remove unused port binding in docker-compose * add quotes to docker compose command * test run * test run * write test script in tests.sh * use docker compose * test run * --rm * ./ -> . * test * change to arm64 * fix docker platform problem * change test os * fix some build bugs * fix runner dir * fix a test case for sample * update cli test to test_install * update test benchmark to improve coverage * remove unused and maintain structured output compatibility * fix evaluator bug * add a test script which contributors can run locally * update contribution guides * add custom model doc (#215)
Configuration menu - View commit details
-
Copy full SHA for e3c9279 - Browse repository at this point
Copy the full SHA e3c9279View commit details -
Configuration menu - View commit details
-
Copy full SHA for 78a8c27 - Browse repository at this point
Copy the full SHA 78a8c27View commit details -
Configuration menu - View commit details
-
Copy full SHA for 88fc3a3 - Browse repository at this point
Copy the full SHA 88fc3a3View commit details
Commits on Oct 12, 2024
-
Configuration menu - View commit details
-
Copy full SHA for 8606b17 - Browse repository at this point
Copy the full SHA 8606b17View commit details -
Configuration menu - View commit details
-
Copy full SHA for 63eab3e - Browse repository at this point
Copy the full SHA 63eab3eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 12060df - Browse repository at this point
Copy the full SHA 12060dfView commit details
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff v0.1.0...v0.1.1