https://github.com/weaviate-tutorials/jdayusa
Weaviate demo for JDayUSA 2023 (semantic search for the Joomla CMS)
https://github.com/weaviate-tutorials/jdayusa
semantic-search weaviate
Last synced: 29 days ago
JSON representation
Weaviate demo for JDayUSA 2023 (semantic search for the Joomla CMS)
- Host: GitHub
- URL: https://github.com/weaviate-tutorials/jdayusa
- Owner: weaviate-tutorials
- Created: 2023-04-13T16:57:09.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-05-18T21:51:21.000Z (over 2 years ago)
- Last Synced: 2025-03-29T06:11:22.941Z (6 months ago)
- Topics: semantic-search, weaviate
- Language: HTML
- Homepage: https://jdayusa.dandv.me
- Size: 1.04 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Joomla + Weaviate - Semantic search
Demo for my [Adding AI-powered semantic search to your Joomla site](https://jdayusa.com/sessions/session-2023/april-22/slot-2-4/adding-ai-powered-semantic-search-to-your-joomla-site) at JDayUSA 2023.
## Usage
1. Set up the project:
```bash
git clone https://github.com/dandv/jdayusa-weaviate
cd jdayusa-weaviate
npm install
2. Optionally update the sessions JSON file. The `sessions.json` from the repo is up-to-date as of 2023-April-13.
```bash
npm run parse # updates sessions.json from jdayusa.com/sessions
3. Create a Weaviate instance. This can be as simple as running the single-executable Linux binary from the [latest release](https://github.com/weaviate/weaviate/releases), or signing up for a [free Weaviate Cloud Services sandbox](https://console.weaviate.cloud), or running a [Docker container](https://weaviate.io/developers/weaviate/installation) locally.
4. Create a `.env` file in the project directory with the following keys:
```text
OPENAI_APIKEY=...get this from https://platform.openai.com/account/api-keys...
# The following two keys are only necessary if you use WCS; not if using Docker
WEAVIATE_HOST=...sign up at https://console.weaviate.cloud and paste the host here (without https)...
WEAVIATE_API_KEY=...get the Admin key from Weaviate Cloud Services...
```
* Take note of the Weaviate cluster hostname, e.g. `localhost:8080` for Docker or `jdayusa-ctv1de32.weaviate.network` if using WCS. Store this in the `.env` file as the `WEAVIATE_HOST`.
* For WCS, click on the cluster Details then the key 🔑 icon and copy the Admin key. Store it as `WEAVIATE_API_KEY` in the `.env` file.
5. Create the Weaviate schema and import the data from the JSON file
```bash
npm run ingest
6. Run the proxy server
```
npm run proxy
You can now run semantic queries via the GraphQL IDE provided by the Weaviate Cloud Services console. You'll need to add your OpenAI API key in the Variables section:
