unstructured
eb1b294b - ML-405/ML-427 - OntologyElement improvements (#3758)

Commit
1 year ago
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
Author
Parents
Loading