https://github.com/weaviate-tutorials/nuxt-multimodal-search
https://github.com/weaviate-tutorials/nuxt-multimodal-search
weaviate-starter
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/weaviate-tutorials/nuxt-multimodal-search
- Owner: weaviate-tutorials
- Created: 2024-06-13T08:11:16.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-04-09T12:31:32.000Z (about 1 year ago)
- Last Synced: 2025-08-21T12:41:12.467Z (9 months ago)
- Topics: weaviate-starter
- Language: Vue
- Homepage:
- Size: 47 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## This is a Multimodal Search demo built with [Weaviate](https://weaviate.io), [Vertex](https://cloud.google.com/vertex-ai) and [Nuxt.js](https://nuxt.com/)
## 🐥 Getting Started
First, clone the project with the command below
```bash
git clone https://github.com/weaviate-tutorials/nuxt-multimodal-search
```
The repository lets us do three things
1. Run the Nuxt.js Web App.
2. Import images, and text into your Weaviate database.
3. Search like it's 2034!
### 🏗️ Create a Weaviate Instance
Create a Weaviate instance on Weaviate Cloud Services as described in [this guide](https://weaviate.io/developers/weaviate/quickstart#step-2-create-an-instance)
### 🦿 Create a `.env` file and add the following keys
- your Google Vertex API key as `NUXT_GOOGLE_API_KEY` (you can get this in your [Vertex AI settings](https://console.cloud.google.com/apis/credentials))
- your Weaviate API key as `NUXT_WEAVIATE_ADMIN_KEY` (you can get this in your [Weaviate dashboard](https://console.weaviate.cloud/dashboard) under sandbox details)
- your Weaviate host URL as `NUXT_WEAVIATE_HOST_URL` (you can get this in your [Weaviate dashboard](https://console.weaviate.cloud/dashboard) under sandbox details)
### 📩 Importing Data
> Before you can import data, add any files to their respective media type in the `public/` folder. You will have to download a dataset of [random images](https://drive.google.com/drive/folders/17QwLNUY2nB9FhKffBD0OIpDI2C0QKdqY?usp=sharing) and place them in `/public/image`. Feel free to use your images too.
With your data in the right folder, run `yarn install` to install all project dependencies and to import your data into Weaviate and initialize a collection, run:
```bash
yarn run import
```
this may take a minute or two.
### 🚀 Running your Nuxt.js Application.
> Make sure you have your Weaviate instance running with data imported before starting your Nuxt.js Web App.
To run the Web App
```bash
yarn dev
```
... and you can search away!!
### 📚 Resources
Learn more about multimodal applications
- [Multimodal Retrieval Augmented Generation(RAG)](https://weaviate.io/blog/multimodal-rag)
- [Multimodal Embedding Models](https://weaviate.io/blog/multimodal-models)
### 🤷🏾♂️ Troubleshooting
- Check out the [Weaviate Docs](https://weaviate.io/developers/weaviate)
- [Open an Issue](https://github.com/malgamves/next-multimodal-search-demo/issues)