Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/tomasonjo/neogpt-explorer

Knowledge-graph based chatbot using GPT3 and Neo4j
https://github.com/tomasonjo/neogpt-explorer

chatbot gpt-3 graph neo4j nlp streamlit

Last synced: 5 days ago
JSON representation

Knowledge-graph based chatbot using GPT3 and Neo4j

Host: GitHub
URL: https://github.com/tomasonjo/neogpt-explorer
Owner: tomasonjo
License: mit
Created: 2023-02-13T09:55:23.000Z (almost 2 years ago)
Default Branch: main
Last Pushed: 2023-06-27T08:37:58.000Z (over 1 year ago)
Last Synced: 2025-01-17T10:06:32.708Z (5 days ago)
Topics: chatbot, gpt-3, graph, neo4j, nlp, streamlit
Language: Jupyter Notebook
Homepage: https://medium.com/neo4j/knowledge-graph-based-chatbot-with-gpt-3-and-neo4j-c4ebbd325ed
Size: 3.08 MB
Stars: 187
Watchers: 9
Forks: 58
Open Issues: 2
Metadata Files:
- Readme: README.md
- License: LICENSE

# NeoGPT-Explorer

Find more information at: https://medium.com/neo4j/knowledge-graph-based-chatbot-with-gpt-3-and-neo4j-c4ebbd325ed

Run the following commands to start the services:

1. Create an `.env` file and input your OPENAI API KEY as shown in `env.example`

2. Start docker services

```
docker-compose up
```

3. On the first run, you need to seed the database with the following command

```
sh seed_database.sh
```

If you are using Windows, you can also execute the `notebooks/Import.ipynb` notebook for initial import

4. Open localhost:8501 in your browser

## Example questions

What are the latest news?

What are the latest news about Apple?

What are the latest news about COVID-19?

What are the latest news about education?

Who was mentioned in a positive light lately?

Most mentioned people in the last 100 articles?

What are the latest facts?

What do you know about Andrew Macintosh?

Where does Ian Chubb work?

What are most mentioned people in sports?

## Data

Testing dataset consists of 1000 latest articles from Kaggle repository: https://www.kaggle.com/datasets/adityakharosekar2/guardian-news-articles

## Preprocessing

The information extraction pipeline was executed with Diffbot API: See `notebooks/Preprocess.ipynb`.

## Feedback

Please create an issue if you have any feedback!