extensityai / symbolicai Goto Github PK
View Code? Open in Web Editor NEWCompositional Differentiable Programming Library
License: BSD 3-Clause "New" or "Revised" License
Compositional Differentiable Programming Library
License: BSD 3-Clause "New" or "Revised" License
Cosine similarity often fails, better use in-context classification for Symbia's capabilities.
Cosine similarity often fails, better use in-context classification for Symbia's capabilities.
Great work on the topic. Really relevant and amazing.
However, I couldn't find documentation regarding running it with local models like llama/vicuna.
Is that something easily achieved?
Simple and intuitive CostTracker for OpenAI api.
Since this library coordinates with a number of other libraries, some of which aren't written in python
, it would be easier for people to use conda
(or its variant mamba
) with an appropriate environment.yml
. This would minimize the need to specify version numbers since one of the strengths of conda
is its ability to solve for version alignment across packages regardless of native programming language, including installing and updating the optimal version of python
.
See this related issue in stackoverflow.
Environment creation:
mamba env create -f environment.yml
Environment update:
mamba env update --file environment.yml --prune
Install failed for me, apparently because the latest python version (11) is incompatible with some of the symbolicai
dependencies.
I got it to install with:
mamba env update --file environment.yml --prune
where:
$ cat environment.yml
name: symbolicai
dependencies:
- python<3.11
- pip:
- symbolicai
When attempting a fresh install of symbolic AI using latest Python 3.12, an exception happens during the pip installation stating:
ModuleNotFoundError: No module named 'distutils'
As far as I am aware, distutils started being phased out in 3.10 and has been completely removed by 3.12. A few solutions of similar problems suggest trying to install setup-tools
but that did not work in my case, and beyond that, the general consensus is for developers to update their solutions to not rely on distutils
.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.