asteval
vectorboard
| asteval | vectorboard | |
|---|---|---|
| 3 | 2 | |
| 0 | 43 | |
| - | - | |
| 7.0 | 5.5 | |
| 2 months ago | 7 months ago | |
| Python | Python | |
| MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
asteval
-
evalidate - Safe evaluation of untrusted user-supplied python expression
There is asteval project. It makes more poweful (ans slower) virtual python interpreter which you can use to run many commands in shared context. My benchmark (100 000 runs of simple python expressions):
-
evalidate: secure eval() for python
If compare to asteval (which is actually has much more features), evalidate is much faster in my benchmarks (benchmark code in repo): 0.017s vs 1.232s
-
A simple, kind-of "safe" eval ?
But, literals are not good enough very often, and one may want to do "len(foo)+bar[i]" , so I went searching trying to find a good implementation. I dug and found asteval, but this issue I raised breaks it for me, apart from the fact that I try not to rely on too many modules beyond the standard library + it has a bunch of peculiarities that make it not a real drop-in replacement to eval().
vectorboard
-
Exploring Methods to Improve Text Chunking in RAG Models (and other things...)
Hi, about chunking, if the text is structured (markdown or html), you can take headding and paragraph as a chunking unit, but the result is also affected by the applied embeddings, which can be evaluated separately first, for standard chunking methods with different chunk lengths, for example with this tool https://github.com/VectorBoard/vectorboard.
-
I created an Open-source framework to optimize and eval RAG embeddings - Vectorboard
Github: https://github.com/Vectorboard/Vectorboard
What are some alternatives?
piston - A high performance general purpose code execution engine.
optuna - A hyperparameter optimization framework
snekbox - Easy, safe evaluation of arbitrary Python code
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
vermin - Concurrently detect the minimum Python versions needed to run code
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
klara - Automatic test case generation for python and static analysis library
evalidate - Safe and fast evaluation of untrusted user-supplied python expressions
chroma - the AI-native open-source embedding database