Skip to content

A simple weaviate demo used for thesis deduplication

License

Notifications You must be signed in to change notification settings

bhuminiecki/weaviate_demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

weaviate_demo

A simple weaviate demo used for thesis deduplication

weaviate

Weaviate documentation can be found here.

compose

Compose files included in this project contain different presets for weaviate install

  • docker-compose.yml - default preset, big 768d english language model with no NER component.
  • docker-compose-en.yml - small 384d english language model with no NER component.
  • docker-compose-multilang.yml - small 384d mutilanguage language model with no NER component.
  • docker-compose-big-ner.yml - big 768d english language model with NER component.
  • docker-compose-small-ner.yml - small 384d english language model with NER component.

usage

Install requirements:

pip install -r requirements.txt

Run docker compose of your choice

cd compose

docker-compose [-f filename] up -d

Prepare your dataset.json file.

Run the indexer

python3 index.py

Start the aplication

streamlit run streamlit_client.py

About

A simple weaviate demo used for thesis deduplication

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages