Releases: langchain-ai/langchain-benchmarks
Releases · langchain-ai/langchain-benchmarks
v0.0.14
What's Changed
- minor: bump to langchain v2 by @baskaryan in #191
- Release 0.0.14 by @baskaryan in #194
Full Changelog: v0.0.13...v0.0.14
v0.0.13
What's Changed
- Update README.md by @eyurtsev in #184
- Update README.md by @eyurtsev in #185
- Update README.md by @eyurtsev in #186
- Update README.md by @eyurtsev in #187
- tool benchmarking by @isahers1 in #190
- Release 0.0.13 by @baskaryan in #192
- infra: release permissions by @baskaryan in #193
New Contributors
Full Changelog: v0.0.12...v0.0.13
v0.0.12
What's Changed
- Update benchmark all for agents by @eyurtsev in #174
- remove tiny multiverse dataset from registry by @eyurtsev in #175
- Update intro, remove adapter by @eyurtsev in #177
- Simplify all tool usage notebooks by @eyurtsev in #178
- Remove old code by @eyurtsev in #176
- Add security policy by @eyurtsev in #180
- Update README.md by @eyurtsev in #181
- Update benchmarks all notebook to use {question} instead of {input} by @eyurtsev in #179
- Update README.md by @eyurtsev in #182
- Release 0.0.12 by @eyurtsev in #183
Full Changelog: v0.0.11...v0.0.12
v0.0.11
What's Changed
- Update README.md to fix archived links by @eyurtsev in #162
- Missing Word in comparing_techniques.ipynb by @MaruthiKo in #160
- Add high cardinality benchmark by @baskaryan in #164
- docs: include high cardinality by @baskaryan in #165
- docs: add high cardinality links by @baskaryan in #166
- update dependencies by @eyurtsev in #167
- update model providers by @eyurtsev in #168
- Add factory for regular tool using agents by @eyurtsev in #169
- Update deps by @eyurtsev in #170
- add tool calling benchmark notebook by @ccurme in #171
- Fix list of env variables in benchmark all notebook by @eyurtsev in #173
New Contributors
- @MaruthiKo made their first contribution in #160
- @baskaryan made their first contribution in #164
- @ccurme made their first contribution in #171
Full Changelog: v0.0.10...v0.0.11
v0.0.10
What's Changed
- Update min langsmith client by @eyurtsev in #132
- Version 0.0.10 by @eyurtsev in #133
- Update benchmark all notebook by @eyurtsev in #134
- Add Anyscale Model by @hinthornw in #135
- Fix openai output parser used by @hinthornw in #138
- Add anthropic agent based on tool user repo by @eyurtsev in #139
- 🐶 by @hinthornw in #136
- Parser Fix by @hinthornw in #142
- Run w/o langsmith by @hinthornw in #137
- Update openai function factory, update benchmark all by @eyurtsev in #143
- OAI Assistant by @hinthornw in #144
- Update example in multiverse math by @eyurtsev in #145
- Update notebooks by @eyurtsev in #146
- Include assistant factory in benchmark all by @hinthornw in #147
- Update Benchmark All by @hinthornw in #148
- Add to toc by @hinthornw in #149
- Add Gemini by @hinthornw in #151
- Update Math Evaluator by @eyurtsev in #152
- Change multiverse math to multiverse math (tiny) and add another multiverse math set by @eyurtsev in #154
- Register the new dataset by @eyurtsev in #155
- Add runnable agent factory by @hinthornw in #156
- Update evaluators by @eyurtsev in #157
- updated
Makefile
by @leo-gan in #153
New Contributors
Full Changelog: v0.0.9...v0.0.10
v0.0.9
What's Changed
- Add semi-structured eval by @rlancemartin in #83
- Minor clean, add Mixtral by @rlancemartin in #123
- Add rate limiter by @eyurtsev in #121
- Bump ruff fix up first party identity for import sorting by @eyurtsev in #124
- Add contains to model registry by @eyurtsev in #126
- remove with_rate_limit from public api by @eyurtsev in #127
- Update fireworks models by @eyurtsev in #128
- Add gemini mm examples by @hinthornw in #125
- Adds custom agents to the langchain benchmarking repo by @eyurtsev in #120
- Add version by @eyurtsev in #130
- Update notebooks, model registry and make release by @eyurtsev in #131
Full Changelog: v0.0.8...v0.0.9
v0.0.8
What's Changed
- Minor cleanup to multi-modal embeddings docs by @rlancemartin in #105
- Update README.md by @eyurtsev in #107
- Update README.md by @eyurtsev in #108
- Add Model Registry by @eyurtsev in #110
- Update model registry by @eyurtsev in #111
- Tool Tasks: Add eval params to task definition by @eyurtsev in #112
- Update evaluator by @hinthornw in #113
- Add mixtral tool use examples by @hinthornw in #114
- Move mixtral models by @hinthornw in #115
- Add gpt-4 models by @eyurtsev in #117
- Benchmark all tool usage notebook by @eyurtsev in #118
- Release 0.0.8 by @eyurtsev in #122
Full Changelog: v0.0.7...v0.0.8
v0.0.7
What's Changed
- Multi modal RAG benchmark by @rlancemartin in #101
- 0.0.7 by @hinthornw in #104
Full Changelog: v0.0.6...v0.0.7
v0.0.6
What's Changed
- Add chat categorization dataset by @hinthornw in #98
- Add Archived by @hinthornw in #53
- Update Chat Extraction Notebook by @hinthornw in #102
Full Changelog: v0.0.5...v0.0.6