NexQuant

mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-08-04 10:47:43 +00:00

Files

T

Xu Yang 768229427d feat: use unified pickle cacher & move llm config into a isolated config (#424 )

* simplify RDAgent conf

* add unified cacher(untested)

* fix small bugs

* fix a bug

* fix a small bug in runner

* use hash_key = None to skip cache

* fix CI

* in factor execution, ignore cache when raise exception

* add file locker to avoid mp calling

* fix CI

* use function __module__ name as folder in cache

2024-10-14 17:34:09 +08:00

extract_knowledge.py

feat: add normal rag into framework (#360 )

2024-09-27 01:36:12 +08:00

graph.py

fix: refine some codes (#353 )

2024-09-27 00:17:28 +08:00

prompts.yaml

fix: fix some bugs in rag (#399 )

2024-09-30 02:38:33 +08:00

README.md

feat: Added support for loading and storing RAG in Kaggle scenarios. (#269 )

2024-09-19 11:33:33 +08:00

vector_base.py

feat: use unified pickle cacher & move llm config into a isolated config (#424 )

2024-10-14 17:34:09 +08:00

README.md

Usage

This folder implements a knowledge base using RAG based on Kaggle competitions. It allows you to store Kaggle competition experiences into the knowledge base, as well as store experimental experiences from RD-Agent.

First, generate a knowledge base (in JSON format) by running the main function in extract_knowledge.py.
Then, create a vector base in vector_base.py and save it.
Finally, add the field KG_RAG_PATH="xxx.pkl" (the path to the saved vector base) in your .env file.