NexQuant/rdagent/scenarios/kaggle/knowledge_management/README.md at dc02e793facbc540cec732012c754a2daf1774e6

mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-08-04 02:37:44 +00:00

Files

T

WinstonLiyt 0166273e15 feat: Added support for loading and storing RAG in Kaggle scenarios. (#269 )

* init a scenario for kaggle feature engineering

* Added support for loading and storing RAG in Kaggle scenarios.

* fix a ci bug

* Add RAG after each experiment's feedback.

* add a promt

* fix a bug

* fix a bug

* add a readme

* refine the code in knowledge loading

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

508 B

Raw Blame History

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.

508 B Raw Blame History

Usage

508 B

Raw Blame History