Skip to main content

Command-line Interface tailored to working with Neo4j Knowledge Graph Databses.

Project description

ICICONSOLE

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.

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 ICICONSOLE
python -m ICICONSOLE

OR

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

First time user setup

You have two options as of now: connecting to a Neo4j database hosted on a Tapis Pod at the Texas Advanced Computing Center, or downloading Neo4j Desktop and connecting to a database that you are running locally.

Tapis

When prompted to change authentication type from Tapis, enter "n". It will then present the default ICICLE base url for tapis, which you can modify by typing "y" to the prompt to change base url.

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

Once you enter your username and password to ICICONSOLE, 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.

Local

If you are running a Neo4j database locally, you will need to download Neo4j Desktop. You can download it here.

Next, you have to run a local dbms. This should be running by default on bolt port 7687, which is what ICICONSOLE will try to connect to.

In ICICONSOLE, when prompted to change authentication type from Tapis, enter "y". Then type "local".

Next, enter any username and graph name; this is just for personalization in the application and not needed for authentication.

The graph password, however, is important. This is the password that you set within Neo4j Desktop for your local database.

First time usage guide

Once you access either a Tapis Pod or your local database, you will be in a custom made console for interfacing with your Knowledge Graph, using the Cypher language. If you know Cypher, you can start typing in commands like

MATCH(n) RETURN n LIMIT 10

If you are not familiar with Cypher, don't worry! This is meant for users who have never used Cypher before. Type in "help" to view some of the built in commands to start exploring the knowledge graph. These commands are very limited however; you can query more creatively and extensively using the power of GPT. Type in the "GPT" command for this. Note that you will need an OpenAI key, which you can get here. You can tell the program to look for your key in a file or environment variable, or simply type it in as input. Then, you can simply type in a query in natural language and get the Cypher code for it.

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

ICICONSOLE-0.8.0.tar.gz (45.9 kB view details)

Uploaded Source

Built Distribution

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

ICICONSOLE-0.8.0-py3-none-any.whl (33.7 kB view details)

Uploaded Python 3

File details

Details for the file ICICONSOLE-0.8.0.tar.gz.

File metadata

  • Download URL: ICICONSOLE-0.8.0.tar.gz
  • Upload date:
  • Size: 45.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.5

File hashes

Hashes for ICICONSOLE-0.8.0.tar.gz
Algorithm Hash digest
SHA256 4ba6fbd3134af9baa8810e66a2c3eb1e975f9e0dfb4306d917c01b15360bf9cb
MD5 3b74cb64660c84091710f3e7cf33a6c6
BLAKE2b-256 fc20b88908e23a63b94b3439983dde5afa743efff5c992b9309929b00920eb54

See more details on using hashes here.

File details

Details for the file ICICONSOLE-0.8.0-py3-none-any.whl.

File metadata

  • Download URL: ICICONSOLE-0.8.0-py3-none-any.whl
  • Upload date:
  • Size: 33.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.5

File hashes

Hashes for ICICONSOLE-0.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d678c586720157856f71d8f48bf35ba786ea698872c6d18bd567a567adc95a93
MD5 eb4c44ccdeca4ddcad109bcc9bb2b0de
BLAKE2b-256 2595a5a38c091232b4ad225de065de4b90cedcc588fa4f24cfafd92571a8778b

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