Giter Site home page Giter Site logo

huchenxucs / chatdb Goto Github PK

View Code? Open in Web Editor NEW
506.0 14.0 46.0 378 KB

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

Home Page: https://chatdatabase.github.io/

Python 100.00%
database large-language-models memory symbolic-execution

chatdb's Introduction

ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

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

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

conda create -n chatdb python=3.9
conda activate chatdb
pip install -r requirements.txt

Add keys

cp .env.template .env
# add OPENAI_API_KEY and MYSQL_PASSWORD

A minimal CLI demo in a fruit shop scenario

python chatdb.py

The CLI demo looks as follows. cli-demo

Citation

If you find our work useful for your research, please consider citing the paper:

@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}
}

chatdb's People

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

chatdb's Issues

Doesn't seem to see a different table schema

I've gone through your codes and paper but still confused about how you passed the table structure to the prompt to let the model know which operations it should take.
I've seen table_schema.py but it only contains fixed SQL sentences.
If this part of the design is missing, does it mean that the experiment is only valid in the fruit shop dataset scenario?

请问为什么在提问的时候会先输出一句“NOT NEED MEMORY”,好像也不会根据数据库来做出回答?

(chatdb) (venv) ErakeedeMacBook-Pro:ChatDB-main erakee$ python chatdb.py
START!
USER INPUT: apple's price
NOT NEED MEMORY: ```
Step1: Retrieve the price of apple
SELECT selling_price
FROM fruits
WHERE fruit_name = 'apple';

USER INPUT: calculate the total revenue for January 2023
NOT NEED MEMORY: ```
Step1: Calculate the total revenue for January 2023
SELECT SUM(total_price) AS total_revenue
FROM sales
WHERE sale_date >= '2023-01-01' AND sale_date < '2023-02-01';

bug

Is there any one facing this problem?
When I run chatdb.py it's shows :

C:\Users\anaconda3\envs\LLM\python.exe C:/User/Desktop/LLM/ChatDB/chatdb.py
Traceback (most recent call last):
  File "C:/Users/Desktop/LLM/ChatDB/chatdb.py", line 7, in <module>
    from call_ai_function import populate_sql_statement
  File "C:\Users\Desktop\LLM\ChatDB\call_ai_function.py", line 36, in <module>
    def populate_sql_statement(sql_str: str, previous_sql_results: list[list[dict]]) -> list[str]:
TypeError: 'type' object is not subscriptable

image

and if I change this def function to:

from typing import List
def populate_sql_statement(sql_str: str, previous_sql_results: List[List[dict]]) -> List[str]:

The result will be like this:
image

Thanks

pymysql.err.OperationalError: (2003, "Can't connect to MySQL server on 'localhost'

运行python chatdb.py后报错

ConnectionRefusedError: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:
pymysql.err.OperationalError: (2003, "Can't connect to MySQL server on 'localhost' ([Errno 111] Connection refused)")

File "/home/Documents/git_clone/ChatDB/mysql.py", line 59, in execute_sql
self.conn.rollback()
AttributeError: 'NoneType' object has no attribute 'rollback'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.