tree-of-thought-puzzle-solver - GitLite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #typescript #golang #android #deep-learning #docker #java #pytorch #security #mcp #openai #open-source

tree-of-thought-puzzle-solver

(★ 376)

The Tree of Thoughts (ToT) framework for solving complex reasoning tasks using LLMs

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- checker.py
- llm.py
- parser.py
- prompter.py
- state.py
- __init__.py
- config.py
- consts.py
- enums.py
- hyperparams.py
- utils.py
- __init__.py
- chatbot_based_solvers.py
- __init__.py
- tot.py
- __init__.py
.gitignore
__init__.py
LICENSE
README.md
requirements.txt
run_expr.py
run_tot.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/jieyilong/tree-of-thought-puzzle-solver

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd tree-of-thought-puzzle-solver

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Tree of Thought Puzzle Solver Demo

This repo implements a Sudoku puzzle solver based on our proposed Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). The ToT technique is inspired by the human mind’s approach for solving complex reasoning tasks through trial and error. In this process, the human mind explores the solution space through a tree-like thought process, allowing for backtracking when necessary. To implement ToT as a software system, we augment an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. In order to solve a given problem, these modules engage in a multi-round conversation with the LLM. Unlike an auto-regressive LLM which generates a new token based on the preceding sequence of tokens without backward editing, the ToT framework allows the sytem to backtrack to the previous steps of the thought-process and explore other directions from there. For more details, please check out our preprint "Large Language Model Guided Tree-of-Thought":

https://arxiv.org/pdf/2305.08291.pdf

## Setup

Clone this repo and install the required dependencies (Python 3.9+ required):

```shell
git clone https://github.com/jieyilong/tree-of-thought-puzzle-solver
cd tree-of-thought-puzzle-solver
pip install -r requirements.txt
touch config.yaml
```

Edit the YAML file `config.yaml`, paste in the following content and save. Then, please set your choice of model (e.g. "gpt-3.5-turbo") and your OpenAI API Key:

```yaml
chatbot:
    type: "openai"
    max_context_length: 8000
    include_chat_history_in_query: false
openai:
    model: <model_name>
    api_key: <your_open_ai_api_key>
```

## Run ToT

```shell
python run_tot.py "<problem_description>"

# Example
python run_tot.py "please solve this 4x4 sudoku puzzle [[*,1,*,*],[*,*,2,*],[*,*,*,4],[1,*,*,*]] where * represents a cell to be filled in."
```

## Run Experiments

```shell
# solver_type: zero_shot, one_shot_with_cot, few_shot_with_cot, tot
python run_expr.py <solver_type> <path/to/problem/set/json>

# Example
python run_expr.py zero_shot data/benchmarks/sudoku/3x3_sudoku_puzzles.json
python run_expr.py one_shot_with_cot data/benchmarks/sudoku/3x3_sudoku_puzzles.json
python run_expr.py few_shot_with_cot data/benchmarks/sudoku/3x3_sudoku_puzzles.json
python run_expr.py tot data/benchmarks/sudoku/3x3_sudoku_puzzles.json
```

## Citation

```bibtex
@misc{long2023llmtot,
      title={Large Language Model Guided Tree-of-Thought}, 
      author={Jieyi Long},
      year={2023},
      eprint={2305.08291},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}
```