https://github.com/flippchen/vectordb-example

https://github.com/flippchen/vectordb-example

Last synced: 25 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/flippchen/vectordb-example
• Owner: Flippchen
• Created: 2024-02-11T21:45:19.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-03-13T21:11:27.000Z (8 months ago)
• Last Synced: 2024-03-14T22:29:32.823Z (8 months ago)
• Language: Rust
• Size: 196 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# VectorDB

This repository contains the code for my presentation about vector databases. The presentation uses the Redis stack.



## Prerequisites

- Docker

- Python >=3.8 or Rust >=1.5

- Running Redis container (see setup.bash)

## How to run

1. Start the Redis container

```bash

./setup.bash

```

2. Run the Python example

```bash

cd python

pip install -r requirements.txt

python3 01_data_upload.py

```

or any other example by changing the name.

2. The rust examples

```bash

cd rust

cargo run --bin 01_data_upload

```

or any other example by changing the name.

For the rust examples you also need to create the index manually. You can do this by running the corresponding python script.

### Running embeddings locally

To run the embeddings locally, you need to download the model first from huggingface. You can do this by running the following command:

```bash

git clone https://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens

```

# Where does the data come from?

The data is from the [The Movie Database](https://www.themoviedb.org/?language=de) dataset. It is a collection of food products from around the world. The data is licensed under the Open Database License. The data was downloaded for a university project in [MovieVerse](https://github.com/ConnActivity/MovieVerse).