34cd281494
benchmarks[major]: bump core to 0.3 ( #211 )
...
- Drop support for python 3.8
- Bump langchain-core to 0.3
- Update pydantic objects to v2
2024-10-21 16:47:14 -04:00
99cf03a50a
add faiss-cpu dependency ( #209 )
2024-08-07 07:53:45 -07:00
b36a339a65
Isaac/realfixes ( #208 )
2024-08-06 15:28:43 -07:00
442cb47fc9
Isaac/realfixes ( #207 )
2024-08-06 15:24:23 -07:00
b7795c7df1
change wd ( #206 )
2024-08-06 15:15:08 -07:00
ac161de968
thanks erick ( #205 )
2024-08-06 14:50:39 -07:00
d91944bb07
test ( #204 )
2024-08-06 14:45:48 -07:00
8798bd3105
test ( #203 )
2024-08-06 14:40:01 -07:00
621eea5d93
Isaac/tryingpoetryagain ( #202 )
2024-08-06 14:36:43 -07:00
b6590a8745
Isaac/changepoetry ( #201 )
2024-08-06 14:30:42 -07:00
458ffa70ea
test ( #200 )
2024-08-06 14:26:56 -07:00
ebe5c117c2
test ( #198 )
2024-08-06 14:14:39 -07:00
adff80af11
docs: update README.md ( #195 )
...
Mutiverse -> Multiverse
2024-07-24 11:13:42 -07:00
301837e303
Release 0.0.14 ( #194 )
2024-07-24 08:00:17 -07:00
4f1d922a6e
minor: bump to langchain v2 ( #191 )
2024-07-24 07:59:19 -07:00
e4e26a3b8e
infra: release permissions ( #193 )
2024-07-24 07:56:47 -07:00
7f82761813
Release 0.0.13 ( #192 )
2024-07-24 07:44:20 -07:00
7e16b6daa6
tool benchmarking ( #190 )
...
Co-authored-by: Bagatur <baskaryan@gmail.com >
2024-07-24 07:00:33 -07:00
22d279a25c
Update README.md ( #187 )
2024-04-19 10:19:19 -04:00
357ada3867
Update README.md ( #186 )
2024-04-18 19:58:54 -04:00
ab2d93ac6d
Update README.md ( #185 )
2024-04-18 13:48:51 -04:00
53f727af64
Update README.md ( #184 )
2024-04-18 13:47:49 -04:00
820af98418
Release 0.0.12 ( #183 )
2024-04-18 13:38:38 -04:00
857f41882f
Update README.md ( #182 )
2024-04-18 11:33:45 -04:00
381ada5cbe
Update benchmarks all notebook to use {question} instead of {input} ( #179 )
...
Update benchmarks all prompt
2024-04-18 11:28:21 -04:00
32a532f269
Update README.md ( #181 )
2024-04-18 11:28:09 -04:00
d0acf0ee26
Add security policy ( #180 )
...
Add security policy
2024-04-18 11:19:13 -04:00
bec40d90ef
Remove old code ( #176 )
...
Remove old code
2024-04-18 11:16:42 -04:00
c80e959b05
Simplify all tool usage notebooks ( #178 )
...
Simplify tool usage notebooks
2024-04-18 11:09:34 -04:00
2007f68302
Update intro, remove adapter ( #177 )
...
Remove confusing adapter for agents. Agent template should just take {question} as the input.
Update intro and simplify it!
2024-04-18 10:47:46 -04:00
aad9045bcb
remove tiny multiverse dataset from registry ( #175 )
...
Keep it for backwards compatibility but do not expose in task registry.
This dataset is probably more confusing to folks than helpful especially
since it it completely overlaps with the existing multiverse math
dataset. We should add another dataset that's later.
2024-04-18 09:31:03 -04:00
3b86e9f0b5
Update benchmark all for agents ( #174 )
2024-04-18 09:23:19 -04:00
c1c5585d3a
Fix list of env variables in benchmark all notebook ( #173 )
...
Fix list of env variables
2024-04-10 22:06:44 -04:00
c45993617b
add tool calling benchmark notebook ( #171 )
...
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com >
2024-04-10 22:03:19 -04:00
d13b33e956
Update deps ( #170 )
...
Update deps
2024-04-10 09:47:14 -04:00
20a4aee5c1
Add factory for regular tool using agents ( #169 )
...
add factory for regular tool using agents
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com >
2024-04-10 09:27:32 -04:00
4139ac8632
update model providers ( #168 )
...
* Update packages to be used with different providers
* Register Anthropic models
2024-04-09 17:44:02 -04:00
89be01737d
update dependencies ( #167 )
...
Update dependencies
2024-04-09 17:17:25 -04:00
29e4e878a4
docs: add high cardinality links ( #166 )
2024-03-13 23:39:42 -07:00
ffc2832088
docs: include high cardinality ( #165 )
2024-03-13 23:09:07 -07:00
8b5feab7b2
Add high cardinality benchmark ( #164 )
2024-03-08 09:10:03 -08:00
a805c985a6
Missing Word in comparing_techniques.ipynb ( #160 )
...
Fixing a missing word in
https://langchain-ai.github.io/langchain-benchmarks/notebooks/retrieval/comparing_techniques.html
The sentence after the heading is incomplete since I have added the word
`documents` which would complete the sentence.
Before changing:
<img width="527" alt="LangChainFix"
src="https://github.com/langchain-ai/langchain-benchmarks/assets/63769209/4859bbf0-19ae-4b87-830d-85f6242b9b61 ">
2024-02-16 15:23:11 -05:00
c0ac497ed4
Update README.md to fix archived links ( #162 )
2024-02-06 12:35:26 -05:00
a0ea197b28
updated Makefile ( #153 )
...
Cleaned up `makefile`
2023-12-20 09:24:06 -05:00
74b11de9ae
Update evaluators ( #157 )
...
Update to remove user warning
2023-12-19 17:30:24 -05:00
c2b70436e5
Add runnable agent factory ( #156 )
...
Not sure if it's "easier" but it involves less thinking about
benchmarking abstractions
2023-12-19 13:39:08 -08:00
af9a9800e5
Register the new dataset ( #155 )
...
Register the new dataset
2023-12-19 15:01:38 -05:00
e7bac2cbb8
Change multiverse math to multiverse math (tiny) and add another multiverse math set ( #154 )
...
* This PR adds a multiverse math consisting of 20 questions.
* Question about rounding has been removed to simplify evaluation.
2023-12-19 14:57:37 -05:00
d595394243
Update Math Evaluator ( #152 )
...
Try another evaluator that ignores the question
2023-12-19 13:52:13 -05:00
27efb7b53c
Add Gemini ( #151 )
2023-12-18 20:27:59 -08:00
ccurme