Skip to main content

GPT Powered Command-line Interface tailored to working with Neo4j Knowledge Graph Databses hosted via Tapis Pods.

Project description

ICICONSOLE-GPT

Overview

ICICONSOLE is designed to provide an efficient and powerful interface to Neo4j Knowledge Graph databases hosted on HPC resources, leveraging Tapis.

This application is specialized for knowledge graph querying, and has some basic CYPHER commands built in.

The difference between ICICONSOLE-GPT and ICICONSOLE is the integration of GPT-3.5 via the OpenAI API. Note that this means to access these features, an OpenAI API key is required; if you don't have one, you can use the rest of the ICICONSOLE features normally.

Installation

Requires Python 3.10 or higher. You can clone this repository and manually install the requirements, or you can directly install the application from PyPi.

pip install ICICONSOLEGPT
python -m ICICONSOLEGPT

OR

git clone https://github.com/AD1616/ICICONSOLE.git
cd ICICONSOLE/ICICONSOLEGPT/ICICONSOLEGPT/
pip install pandas
pip install py2neo
pip install tapipy
pip install datascroller
pip install openai
python __main__.py

First time user guide

You will be asked to login with your TACC account. If you aren't sure if you have this, visit the TACC portal.

Next, you will see the Tapis Pods that you have been given permission to access. If you don't see any, please contact the owner of the Pod you wish to access. Type in the ID of the Pod that you want to access.

Once you do this, you will be in a custom made console for interfacing with the Knowledge Graph, using the Cypher language. If you know Cypher, you can start typing in commands like

MATCH(n) RETURN n LIMIT 10

The key feature of this is that in addition to the built in commands with ICICONSOLE, this application also has the ability to use GPT-3.5 to generate Cypher queries. To do this, use the "GPT" command once in the console, and then enter a query in natural language.

The welcome message for the Knowledge Graph console contains helpful tips, like "new", "exit", "clear", and "help".

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ICICONSOLEGPT-0.0.6.tar.gz (8.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ICICONSOLEGPT-0.0.6-py3-none-any.whl (9.7 kB view details)

Uploaded Python 3

File details

Details for the file ICICONSOLEGPT-0.0.6.tar.gz.

File metadata

  • Download URL: ICICONSOLEGPT-0.0.6.tar.gz
  • Upload date:
  • Size: 8.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.5

File hashes

Hashes for ICICONSOLEGPT-0.0.6.tar.gz
Algorithm Hash digest
SHA256 4d4887a8c5e1c2e7d3a5d5bd2c94531d1e96b91836b4fbcd2cc31d88c2947290
MD5 630ae014dc4b77701b2a87059b78037e
BLAKE2b-256 029361b5fba70d7d3aa94b642622b3fa32030406561b5798eae15111eb5614fb

See more details on using hashes here.

File details

Details for the file ICICONSOLEGPT-0.0.6-py3-none-any.whl.

File metadata

  • Download URL: ICICONSOLEGPT-0.0.6-py3-none-any.whl
  • Upload date:
  • Size: 9.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.5

File hashes

Hashes for ICICONSOLEGPT-0.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 2e6d5e98558798fec97258fcf1c9f6835fc330f0f0e3f3cfa9ea23ec3f0aaa3d
MD5 74c4eb0cc6f432141ca8bdd09d653e18
BLAKE2b-256 b0b710ed9e36a431b9f3b56f54b9cc5c3f3cf1c23ad6d8c32db19fa8bdb21054

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page