https://github.com/olivervea/elasticembeddings

ElasticEmbeddings is a simple application, which exposes an API for semantic search. The semantic search is done with OpenAI embeddings and Elasticsearch.
https://github.com/olivervea/elasticembeddings

asp-net elasticsearch openai semantic-search

Last synced: 5 days ago
JSON representation

ElasticEmbeddings is a simple application, which exposes an API for semantic search. The semantic search is done with OpenAI embeddings and Elasticsearch.

• Host: GitHub
• URL: https://github.com/olivervea/elasticembeddings
• Owner: OliverVea
• Created: 2023-12-06T05:26:26.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-28T05:07:25.000Z (about 1 year ago)
• Last Synced: 2024-12-12T20:16:37.990Z (2 months ago)
• Topics: asp-net, elasticsearch, openai, semantic-search
• Language: C#
• Homepage:
• Size: 234 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ElasticEmbeddings

ElasticEmbeddings is a simple application, which exposes an API for [semantic search](https://www.elastic.co/what-is/semantic-search).

The semantic search is done with [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings) and [Elasticsearch](https://www.elastic.co/guide/en/elasticsearch/reference/current/semantic-search.html).

## Usage

This application is intended to run in docker. 

For the sake of convenience, a [`docker-compose.yml`](docker-compose.yml) file is provided, containing an Elasticsearch instance and the application itself.

### Running the application

1. Ensure that you have a valid Azure OpenAI API key.

1. Copy the [`.env.template`](.env.template) file to `.env` and fill in the values.

2. Run the application with:

    ```bash

    docker-compose up -d

    ```

3. The API is now available at [`http://localhost:8080/swagger/index.html`](http://localhost:8080/swagger/index.html).

### Demo

An IPython notebook is provided to demonstrate the usage of the API. It can be found in [`demo.ipynb`](demo.ipynb).