Skip to content

MuyaoLi-jimo/NLP_RAT

Repository files navigation

NLP_RAG

Repository Structure

  • /src
    • /dataset
      • collect_data.py - collect data api
      • DataHelper.py
    • /evaluate
      • evaluate.py - evaluate api
    • /Method
      • Method.py - function api
      • rag.py - rag system
      • rat_tools.py - the tool for RAT
    • /utils
      • api_utils.py - Utility functions for interacting with the Deepseek-v2 API.
      • file_utils.py - Functions for file manipulation and storage handling.
      • mp_utils.py - Utilities for multiprocessing and data handling.
    • /visial
    • gaokao_obj.py - the main tunnel for gaokao benchmark
    • mbpp.py
  • /examples
    • rat_tools.py
    • techniques.py
    • test.ipynb
  • /docs
    • proposal.md
  • /lib
    • /GAOKAO-Bench
  • /logs
  • .gitignore - Specifies intentionally untracked files to ignore.
  • README.MD - Describes the project, its structure, and how to run the scripts.
  • requirements.txt - Lists all the dependencies necessary to run the project.

Setup and Installation

  1. Clone the repository: $ pip install -r requirements
  2. Add the api_key: $ export DEEPSEEK_API_KEY="XXXXXX"
  3. run the code: $ python gaokao_obj.py --model_name DeepSeek-V3

rag resource

About

北京大学FNLP课程大作业

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages