github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-10-03 03:08:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
eee2f23a7945f25e2ddd35cbfcf9862d65e15a2d
langchain/docs/use_cases/evaluation
History
vowelparrot 5ca7ce77cd Remove pythonrepl from LLM-MathChain (#2943) 
Use numexpr evaluate instead of the python REPL to avoid malicious code
injection.

Tested against the (limited) math dataset and got the same score as
before.

For more permissive tools (like the REPL tool itself), other approaches
ought to be provided (some combination of Sanitizer + Restricted python
+ unprivileged-docker + ...), but for a calculator tool, only
mathematical expressions should be permitted.

See https://github.com/hwchase17/langchain/issues/814
2023-04-16 08:50:32 -07:00
..
agent_benchmarking.ipynb
Remove pythonrepl from LLM-MathChain (#2943)
2023-04-16 08:50:32 -07:00
agent_vectordb_sota_pg.ipynb
bump version to 131 (#2391)
2023-04-04 07:21:50 -07:00
benchmarking_template.ipynb
Harrison/agent eval (#1620)
2023-03-14 12:37:48 -07:00
data_augmented_question_answering.ipynb
Typo docs - Update data_augmented_question_answering.ipynb propriterary-> proprietary (#2626)
2023-04-09 12:24:53 -07:00
huggingface_datasets.ipynb
Update huggingface_datasets.ipynb (#1417)
2023-03-04 00:22:31 -08:00
llm_math.ipynb
Harrison/llm math (#1808)
2023-03-20 07:53:26 -07:00
openapi_eval.ipynb
Harrison/move eval (#2533)
2023-04-07 07:53:13 -07:00
qa_benchmarking_pg.ipynb
WIP: Harrison/base retriever (#1765)
2023-03-24 07:46:49 -07:00
qa_benchmarking_sota.ipynb
WIP: Harrison/base retriever (#1765)
2023-03-24 07:46:49 -07:00
qa_generation.ipynb
Harrison/agent eval (#1620)
2023-03-14 12:37:48 -07:00
question_answering.ipynb
fix typo (#2532)
2023-04-07 07:25:22 -07:00
sql_qa_benchmarking_chinook.ipynb
Harrison/agent eval (#1620)
2023-03-14 12:37:48 -07:00