v0.14.0

What's Changed

• feat: add support for js functions as scorer by @saikatmitra91 in #230
• feat: deprecate init command by @saikatmitra91 in #229
• chore: update package versions for release by @github-actions in #232
• chore(deps): bump requests from 2.31.0 to 2.32.0 in /examples/rag by @dependabot in #231
• docs: add readme for create-empiricalrun package by @saikatmitra91 in #228

Full Changelog: https://github.com/empirical-run/empirical/compare/empiricalrun@0.13.2...empiricalrun@0.14.0

v0.13.2

What's Changed

• feat: easier TS and JS config creation using npm init command by @saikatmitra91 in #222
• fix: reduce package size of empiricalrun CLI by @saikatmitra91 in #226

Full Changelog: https://github.com/empirical-run/empirical/compare/empiricalrun@0.13.1...empiricalrun@0.13.2

v0.13.1

What's Changed

• docs: update docs with new empirical CLI package name by @saikatmitra91 in #224

Full Changelog: https://github.com/empirical-run/empirical/compare/empiricalrun@0.13.0...empiricalrun@0.13.1

v0.13.0

Breaking Changes

• Deprecated packages @empiricalrun/cli and @empiricalrun/core. The packages have been merged into a single package named empiricalrun

What's Changed

• feat: add js and ts config support by @saikatmitra91 in #218
• fix: latency calculation for claude, gemini, gpt chat by @arjunattam in #216
• fix: google ai provider throwing 503 service unavailable by @saikatmitra91 in #220
• docs: tool calling and improvement to models section by @arjunattam in #217

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.12.0...empiricalrun@0.13.0

v0.12.1

What's Changed

• fix: latency calculation for claude, gemini, gpt chat by @arjunattam in #216
• fix: google ai provider throwing 503 service unavailable by @saikatmitra91 in #220
• docs: tool calling and improvement to models section by @arjunattam in #217

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.12.0...@empiricalrun/cli@0.12.1

v0.12.0

What's Changed

• feat: add support for grouping inputs by @saikatmitra91 in #215
• docs: openai assistants by @arjunattam in #209
• docs: add support for JSON dataset by @saikatmitra91 in #212
• chore(deps): bump jinja2 from 3.1.3 to 3.1.4 in /examples/rag by @dependabot in #214

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.11.0...@empiricalrun/cli@0.12.0

v0.11.0

What's Changed

• feat: add tools support for models by @saikatmitra91 in #203
• feat(interactivity): support editing for all samples by @arjunattam in #127
• fix: add support for azure base URL by @arushsharma24 in #207
• fix: cli summary shows all run-specific scores by @mukeshblackhat in #205
• fix: handle rate_limit_exceeded in openai assistants by @arjunattam in #210
• chore: update package versions for release by @github-actions in #208
• chore(deps): bump tqdm from 4.66.2 to 4.66.3 in /examples/rag by @dependabot in #206
• docs: readme intro and video by @arjunattam in #197

New Contributors

• @arushsharma24 made their first contribution in #207
• @mukeshblackhat made their first contribution in #205

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.10.0...@empiricalrun/cli@0.11.0

v0.10.0

What's Changed

• feat: add support for tool calls in UI by @saikatmitra91 in #199
• feat: add support for tools in assistant run config parameters by @saikatmitra91 in #202
• feat: add dedicated edit UI for assistant instructions by @saikatmitra91 in #200
• fix: fireworks errors are absorbed by @arjunattam in #195
• fix: output and dataset alignment issues in UI by @saikatmitra91 in #201
• fix: overlapping outputs by @saikatmitra91 in #204

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.9.1...@empiricalrun/cli@0.10.0

v0.9.1

What's Changed

• feat: CSV loader should parse numbers by @arjunattam in #190
• feat: add support for assistant run config defaults by @saikatmitra91 in #188
• feat: py-script scorer has a simpler return type by @arjunattam in #193
• fix: add retry logs by @saikatmitra91 in #192
• ci: auto-upload json schema on npm publish by @arjunattam in #187
• chore: remove sql semantic scorer by @arjunattam in #191
• chore: update run telemetry events by @arjunattam in #194

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.9.0...@empiricalrun/cli@0.9.1

v0.9.0

What's Changed

• feat: ability to add global scorers by @saikatmitra91 in #178
• feat: openai assistants by @arjunattam in #174
• fix: py-script getting timed out by @saikatmitra91 in #183
• feat: add telemetry for usage analytics by @arjunattam in #182
• fix: errors in assistant and basic examples by @saikatmitra91 in #186
• chore: update default init config for global scorers by @arjunattam in #180
• chore: change scorer names to json-syntax and llm-critic by @arjunattam in #181
• chore: better error message for scorer name changes by @arjunattam in #185

Full Changelog: https://github.com/empirical-run/empirical/compare/@empiricalrun/cli@0.8.0...@empiricalrun/cli@0.9.0