Difference between revisions of "Weaviate"
Jump to navigation
Jump to search
(18 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
+ | * https://github.com/semi-technologies/weaviate | ||
+ | |||
<youtube>https://youtu.be/3NfcAF4qm2k</youtube> | <youtube>https://youtu.be/3NfcAF4qm2k</youtube> | ||
see | see | ||
* https://www.semi.technology/news/fosdem-2020.html | * https://www.semi.technology/news/fosdem-2020.html | ||
* https://www.semi.technology/documentation/weaviate/current/about/philosophy.html#about-the-contextionary | * https://www.semi.technology/documentation/weaviate/current/about/philosophy.html#about-the-contextionary | ||
− | * Word2vec | + | * {{Link|target=Word2vec}} |
− | * BERT | + | * {{Link|target=BERT}} |
− | * | + | * {{Link|target=GloVe}} |
+ | |||
+ | Fill with dictionary "e.g. english". | ||
+ | <youtube>SDOl9fRObVg</youtube> | ||
+ | * https://stackoverflow.com/questions/27652335/semantic-search-engines/60361878#60361878 | ||
+ | * https://www.semi.technology/news/fosdem-2020.html | ||
+ | * https://en.wikipedia.org/wiki/Bob_van_Luijt | ||
+ | * [http://playground.semi.technology/?weaviate_uri=https%3A%2F%2Fdemo.dataset.playground.semi.technology%2Fv1%2Fgraphql&gqlquery=%7B%0D%0A++Get%7B%0D%0A++++Things%7B%0D%0A++++++Publication%28%0D%0A++++++++explore%3A+%7B%0D%0A++++++++++concepts%3A+%5B%22fashion%22%5D%2C%0D%0A++++++++++certainty%3A+0.7%2C%0D%0A++++++++++moveAwayFrom%3A+%7B%0D%0A++++++++++++concepts%3A+%5B%22finance%22%5D%2C%0D%0A++++++++++++force%3A+0.45%0D%0A++++++++++%7D%2C%0D%0A++++++++++moveTo%3A+%7B%0D%0A++++++++++++concepts%3A+%5B%22haute+couture%22%5D%2C%0D%0A++++++++++++force%3A+0.85%0D%0A++++++++++%7D%0D%0A++++++++%7D%0D%0A++++++%29%7B%0D%0A++++++++name%0D%0A++++++%7D%0D%0A++++%7D%0D%0A++%7D%0D%0A%7D&graphiql Weaviate playground] | ||
+ | * https://www.semi.technology/documentation/weaviate/current/about/philosophy.html#about-the-contextionary | ||
+ | |||
+ | * https://nlp.stanford.edu/pubs/glove.pdf | ||
+ | * http://wiki.bitplan.com/index.php/Weaviate | ||
+ | * https://hackernoon.com/how-weaviates-graphql-api-was-designed-t93932tl | ||
+ | * https://medium.com/semi-technologies/finding-answers-in-complex-standardizations-documents-using-weaviates-semantic-search-modules-4dcdb83527fb | ||
+ | = Versions = | ||
+ | * https://medium.com/semi-technologies/weaviate-version-1-2-x-now-supports-transformer-models-4a12d858cce3 | ||
+ | |||
+ | = Presentations = | ||
+ | <youtube>DCQWqMecdlA</youtube> | ||
+ | <youtube>Ufs0cU-gaeM</youtube> | ||
+ | |||
+ | = Installation = | ||
+ | see https://weaviate.io/developers/weaviate/installation | ||
+ | == Setup, schema, importing data and GraphQL == | ||
+ | <youtube>L0Y_zZR8FRI</youtube> | ||
+ | == Docker == | ||
+ | === Prerequisites === | ||
+ | <source lang='bash'> | ||
+ | sudo apt-get install curl docker docker-compose | ||
+ | </source> | ||
+ | |||
+ | === Installweaviate === | ||
+ | <source lang='bash' highlight='1,9,10'> | ||
+ | git clone https://github.com/weaviate/weaviate.git | ||
+ | Cloning into 'weaviate'... | ||
+ | remote: Enumerating objects: 124394, done. | ||
+ | remote: Counting objects: 100% (14150/14150), done. | ||
+ | remote: Compressing objects: 100% (1626/1626), done. | ||
+ | remote: Total 124394 (delta 12845), reused 13458 (delta 12510), pack-reused 110244 | ||
+ | Receiving objects: 100% (124394/124394), 945.83 MiB | 33.55 MiB/s, done. | ||
+ | Resolving deltas: 100% (86422/86422), done. | ||
+ | cd weaviate | ||
+ | docker build --target weaviate -t weaviate . | ||
+ | docker compose up | ||
+ | </source> | ||
+ | |||
+ | == docker-compose.yml == | ||
+ | <source lang='yaml'> | ||
+ | version: '3.4' | ||
+ | services: | ||
+ | weaviate: | ||
+ | image: weaviate | ||
+ | ports: | ||
+ | - 8080:8080 | ||
+ | environment: | ||
+ | CONTEXTIONARY_URL: contextionary:9999 | ||
+ | QUERY_DEFAULTS_LIMIT: 25 | ||
+ | AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true' | ||
+ | PERSISTENCE_DATA_PATH: './data' | ||
+ | ENABLE_MODULES: 'text2vec-contextionary' | ||
+ | DEFAULT_VECTORIZER_MODULE: 'text2vec-contextionary' | ||
+ | AUTOSCHEMA_ENABLED: 'false' | ||
+ | contextionary: | ||
+ | environment: | ||
+ | OCCURRENCE_WEIGHT_LINEAR_FACTOR: 0.75 | ||
+ | EXTENSIONS_STORAGE_MODE: weaviate | ||
+ | EXTENSIONS_STORAGE_ORIGIN: http://localhost:8080 | ||
+ | NEIGHBOR_OCCURRENCE_IGNORE_PERCENTILE: 5 | ||
+ | ENABLE_COMPOUND_SPLITTING: 'false' | ||
+ | image: semitechnologies/contextionary:en0.16.0-v1.2.1 | ||
+ | </source> | ||
+ | |||
+ | == Installation Issue == | ||
+ | * https://github.com/semi-technologies/weaviate/issues/1215 | ||
+ | == Python Library == | ||
+ | * https://www.semi.technology/documentation/weaviate/current/client-libs/python.html | ||
[[Category:SiGNaL]] | [[Category:SiGNaL]] | ||
+ | == sample code == | ||
+ | === Integration tests === | ||
+ | * https://github.com/semi-technologies/weaviate-python-client/blob/master/integration/client_functions.py | ||
+ | |||
+ | = Videos = | ||
+ | <youtube>Gd5Fx0fOdfA</youtube> | ||
+ | <youtube>tKGRyzelDjU</youtube> |
Latest revision as of 10:19, 10 June 2023
see
- https://www.semi.technology/news/fosdem-2020.html
- https://www.semi.technology/documentation/weaviate/current/about/philosophy.html#about-the-contextionary
- Word2vec
- BERT
- GloVe
Fill with dictionary "e.g. english".
- https://stackoverflow.com/questions/27652335/semantic-search-engines/60361878#60361878
- https://www.semi.technology/news/fosdem-2020.html
- https://en.wikipedia.org/wiki/Bob_van_Luijt
- Weaviate playground
- https://www.semi.technology/documentation/weaviate/current/about/philosophy.html#about-the-contextionary
- https://nlp.stanford.edu/pubs/glove.pdf
- http://wiki.bitplan.com/index.php/Weaviate
- https://hackernoon.com/how-weaviates-graphql-api-was-designed-t93932tl
- https://medium.com/semi-technologies/finding-answers-in-complex-standardizations-documents-using-weaviates-semantic-search-modules-4dcdb83527fb
Versions
Presentations
Installation
see https://weaviate.io/developers/weaviate/installation
Setup, schema, importing data and GraphQL
Docker
Prerequisites
sudo apt-get install curl docker docker-compose
Installweaviate
git clone https://github.com/weaviate/weaviate.git
Cloning into 'weaviate'...
remote: Enumerating objects: 124394, done.
remote: Counting objects: 100% (14150/14150), done.
remote: Compressing objects: 100% (1626/1626), done.
remote: Total 124394 (delta 12845), reused 13458 (delta 12510), pack-reused 110244
Receiving objects: 100% (124394/124394), 945.83 MiB | 33.55 MiB/s, done.
Resolving deltas: 100% (86422/86422), done.
cd weaviate
docker build --target weaviate -t weaviate .
docker compose up
docker-compose.yml
version: '3.4'
services:
weaviate:
image: weaviate
ports:
- 8080:8080
environment:
CONTEXTIONARY_URL: contextionary:9999
QUERY_DEFAULTS_LIMIT: 25
AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
PERSISTENCE_DATA_PATH: './data'
ENABLE_MODULES: 'text2vec-contextionary'
DEFAULT_VECTORIZER_MODULE: 'text2vec-contextionary'
AUTOSCHEMA_ENABLED: 'false'
contextionary:
environment:
OCCURRENCE_WEIGHT_LINEAR_FACTOR: 0.75
EXTENSIONS_STORAGE_MODE: weaviate
EXTENSIONS_STORAGE_ORIGIN: http://localhost:8080
NEIGHBOR_OCCURRENCE_IGNORE_PERCENTILE: 5
ENABLE_COMPOUND_SPLITTING: 'false'
image: semitechnologies/contextionary:en0.16.0-v1.2.1
Installation Issue
Python Library
sample code
Integration tests
Videos