ChatDB - GitLite

KO | EN

gitlite — search

#react #ai #golang #go #android #rust #macos #nodejs #java #windows #cli #ios #mcp #open-source

ChatDB

(★ 605)

The official repository of "ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory".

파일 탐색기

최종 버전 다운로드 (.zip)

- cli_demo.jpeg
- teaser.png
- customers.csv
- fruits.csv
- purchase_items.csv
- purchases.csv
- sale_items.csv
- sales.csv
- suppliers.csv
.env.template
.gitignore
call_ai_function.py
chat.py
chatdb.py
chatdb_prompts.py
chatgpt.py
config.py
fruit_shop_schema.py
logger.py
mysql.py
README.md
requirements.txt
sql_examples.py
tables.py
token_counter.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/huchenxucs/ChatDB

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd ChatDB

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)

# ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

### [Paper](https://arxiv.org/abs/2306.03901) | [Project Page](https://chatdatabase.github.io/)

This is the official repository of the paper: **ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory**.

**We will continuously add new features to this code repository. Please stay tuned!**

![teaser](https://raw.githubusercontent.com/huchenxucs/ChatDB/main/assets/teaser.png)

Large language models (LLMs) with memory are computationally universal.
However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains.
Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning.
In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning.
Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases.
We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning.

## Quick Start
### Install dependencies
```bash
conda create -n chatdb python=3.9
conda activate chatdb
pip install -r requirements.txt
```

### Add keys
```bash
cp .env.template .env
# add OPENAI_API_KEY and MYSQL_PASSWORD
```

### A minimal CLI demo in a fruit shop scenario
```bash
python chatdb.py
```
The CLI demo looks as follows.
![cli-demo](https://raw.githubusercontent.com/huchenxucs/ChatDB/main/assets/cli_demo.jpeg)

## Citation
If you find our work useful for your research, please consider citing the paper:
```bash
@misc{hu2023chatdb,
      title={ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory},
      author={Chenxu Hu and Jie Fu and Chenzhuang Du and Simian Luo and Junbo Zhao and Hang Zhao},
      year={2023},
      eprint={2306.03901},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}
```