https://github.com/weaviate-tutorials/cohere-wiki-multilingual
How to use Weaviate semantic search and generative search with Cohere
https://github.com/weaviate-tutorials/cohere-wiki-multilingual
Last synced: 10 months ago
JSON representation
How to use Weaviate semantic search and generative search with Cohere
- Host: GitHub
- URL: https://github.com/weaviate-tutorials/cohere-wiki-multilingual
- Owner: weaviate-tutorials
- Created: 2023-02-17T21:06:25.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-10-15T18:27:42.000Z (over 2 years ago)
- Last Synced: 2025-02-03T18:11:23.618Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 49.8 KB
- Stars: 1
- Watchers: 5
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# Semantic Search and Generative Search with Cohere
This project contain two Jupyter Notebooks:
* `wiki-large-setup` – shows how to configure a collection with `text2vec-cohere` and `generative-cohere` modules. Then loads pre-vectorized Wikipedia data in 10 different languages
* `wiki-large-query` – examples for Semantic Search and Generative Search queries
## Load data
Notes:
* collection name: `Wikipedia`
* languages included: `en`, `de`, `fr`, `es`, `it`, `ja`, `ar`, `zh`, `ko`, `hi`
* source: [Cohere/wikipedia-22-12-(lang)-embeddings](https://huggingface.co/Cohere)
## How to use
To make this notebook work on your own Weaviate instance, you need to update or provide:
- `access_token` – auth token used to authenticate with your Weaviate instance. Note, if your Weaviate instance is configured without authentication, then you can remove the whole `auth_config`.
- `url` – provide the url for your Weaviate instance
- `X-Cohere-Api-Key` – this is your API key you need to get from [dashboard.cohere.ai/api-keys](https://dashboard.cohere.ai/api-keys)
### WCS configuration
Weaviate instances created with WCS provide all the required modules. No action required.
### Instances deployed with Docker
Make sure that your docker configuration includes the following modules:
* `text2vec-cohere`
* `generative-cohere`