Maksymilian Operlejn eb1b294b73

ML-405/ML-427 - OntologyElement improvements (#3758) ...

- the "value" attribute from <input/> tag will be taken into account and
processed as "text" in ontology
- the tables will now be parsed without any ids and classes - we have
different reasons behind that, for example, embeddings with ids and
classes can lose some semantic value. Also, more tokens = more expensive
LLM call
-  cleaned to_html, created to_text for OntologyElement

2024-10-31 01:30:53 +00:00

..

example.json

ML-405/ML-427 - OntologyElement improvements (#3758)

2024-10-31 01:30:53 +00:00