- Enrichment: transforming unstructured documents into rich, structured, hierarchical knowledge graphs representing key sections, concepts, entities, and their relationships to one another.
- Embedding: transforming queries and documents into highly compressed, high fidelity numerical representations to power semantic search, text classification, and clustering.
- Reranking: scoring and sorting documents based on their relevance to search queries.
- Extractive question answering: extracting answers to questions from documents with high precision and throughput.
- Universal classification: classifying and extracting clauses from documents based on your own criteria, with no prior examples necessary.